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

    Neuronpedia

    INDEX
    Explanations

    references to "fool" or "fools" in various contexts

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

    fool and foolishness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onyx
    -0.52
     Onyx
    -0.50
     Nowak
    -0.50
     Aria
    -0.48
    asString
    -0.47
     Karina
    -0.46
     MIA
    -0.46
     atx
    -0.46
     Ona
    -0.45
     Parkes
    -0.45
    POSITIVE LOGITS
     Fool
    2.03
     fool
    1.93
    Fool
    1.91
    fool
    1.84
     Fools
    1.74
     fools
    1.66
     fooling
    1.14
     fooled
    1.00
     foolish
    0.92
    Fo
    0.89
    Act Density 0.003%

    No Known Activations