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

    Neuronpedia

    INDEX
    Explanations

    function calls related to output formatting

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

    Follows common punctuation or prepositions

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    -0.62
     
    -0.60
     J
    -0.57
     j
    -0.56
     sk
    -0.55
    ly
    -0.54
     le
    -0.52
    {
    -0.51
     e
    -0.51
     I
    -0.50
    POSITIVE LOGITS
     itſelf
    1.20
     toString
    1.11
     Monfieur
    1.10
     Theſe
    1.06
     myſelf
    1.04
    toString
    1.04
     Anſ
    1.03
    InputBorder
    1.03
     Houſe
    1.02
     himſelf
    1.01
    Act Density 0.043%

    No Known Activations