Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    indicators of formal document structure or citation.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressions related to coding and technical application instructions.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    the start of a new sentence or paragraph, particularly after quotation marks or at the beginning of a document.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Follows punctuation or special characters

    np_acts-logits-general · gemini-2.0-flash

    end of sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UrlResolution
    -1.04
    ̯
    -0.65
    ItemModel
    -0.63
    TagHelpers
    -0.55
    ("")
    -0.55
    érience
    -0.55
    CodedInputStream
    -0.54
    thode
    -0.54
    ━━━━━━━━
    -0.53
    LEncoder
    -0.53
    POSITIVE LOGITS
     Monfieur
    1.02
     poffible
    0.90
     Efq
    0.85
     myſelf
    0.85
     purpoſe
    0.84
     seyn
    0.82
     ſeveral
    0.78
    いる
    0.78
    ).)
    0.75
     Chriftian
    0.74
    Act Density 0.182%

    No Known Activations