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

    Neuronpedia

    INDEX
    Explanations

    paragraph breaks or transitions between sections of text.

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

    distinct segments of text that express a range of values or categories.

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

    numerical values or code snippets.

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

    Preceding word ends with "t" or "s"

    np_acts-logits-general · gemini-2.0-flash

    formal or archaic wording

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.81
    TagMode
    -0.77
     AssemblyVersion
    -0.77
    LookAnd
    -0.75
    setVerticalGroup
    -0.73
     estekak
    -0.72
    InjectAttribute
    -0.72
     MainAxisSize
    -0.68
    Personensuche
    -0.67
    WithIOException
    -0.63
    POSITIVE LOGITS
    ↵↵
    0.83
     itſelf
    0.70
     Theſe
    0.65
     Efq
    0.65
     Eſ
    0.59
     myſelf
    0.59
     Reſ
    0.58
    It
    0.58
     It
    0.58
     ſch
    0.57
    Act Density 0.103%

    No Known Activations