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

    Neuronpedia

    INDEX
    Explanations

    closed sentences and punctuation marks, indicating the end of thoughts

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

    Follows a quotation

    np_acts-logits-general · gemini-2.0-flash

    end quote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    -0.73
    "
    -0.72
     nahilalakip
    -0.61
    SourceChecksum
    -0.60
    ",
    -0.60
     CreateTagHelper
    -0.58
    ：
    -0.56
    principalColumn
    -0.56
    '',
    -0.54
    :],
    -0.54
    POSITIVE LOGITS
     adding
    0.86
    Adding
    0.81
    Added
    0.77
     Adding
    0.76
    adding
    0.74
     “…
    0.73
     added
    0.72
     “...
    0.70
     Added
    0.70
     referring
    0.69
    Act Density 0.022%

    No Known Activations