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

    Neuronpedia

    INDEX
    Explanations

    mentions of or references to "anyone"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "anyone."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.73
    iger
    -0.71
    irth
    -0.67
    urations
    -0.66
    ÃŁ
    -0.63
    ulk
    -0.62
    itals
    -0.62
     Maze
    -0.61
    omorph
    -0.61
    icons
    -0.60
    POSITIVE LOGITS
     else
    1.84
     Else
    1.26
    else
    1.22
    Else
    1.20
    THING
    1.08
     doubted
    0.95
    20439
    0.93
     who
    0.93
     imaginable
    0.88
    soever
    0.84
    Act Density 0.030%

    No Known Activations