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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that express hypothetical situations

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

    if you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteLiteral
    -0.56
     accordingly
    -0.39
     locations
    -0.38
     broche
    -0.37
    stdbool
    -0.36
     пожалуйста
    -0.36
    WireFormatLite
    -0.36
     laser
    -0.35
     Photographie
    -0.35
     possibly
    -0.34
    POSITIVE LOGITS
    Autoritní
    0.78
    FormTagHelper
    0.62
     autorytatywna
    0.60
    SequentialGroup
    0.59
    istoitu
    0.57
    الدراسه
    0.57
    GEBURTSDATUM
    0.57
     كومونز
    0.57
    IsContent
    0.55
    tonode
    0.54
    Act Density 0.020%

    No Known Activations