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

    Neuronpedia

    INDEX
    Explanations

    the word "freak" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    the term "freak" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adr
    -0.76
     conduc
    -0.71
    ea
    -0.71
    undai
    -0.70
    ournal
    -0.69
     Liberties
    -0.69
    ript
    -0.67
    eger
    -0.67
    vette
    -0.65
    HAEL
    -0.63
    POSITIVE LOGITS
    ishly
    1.37
    ously
    1.07
    onom
    1.05
    istically
    0.97
    show
    0.96
    ery
    0.85
    ish
    0.84
    ageddon
    0.84
    erers
    0.84
    iness
    0.83
    Act Density 0.041%

    No Known Activations