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

    Neuronpedia

    INDEX
    Explanations

    references to "subject" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.11
    丹
    -0.64
    public
    -0.64
    int
    -0.63
    //@
    -0.61
    /*++
    -0.60
     realize
    -0.59
     Italijani
    -0.59
     win
    -0.59
    estacks
    -0.59
    POSITIVE LOGITS
     increa
    1.63
     stockholm
    1.61
     Juf
    1.58
     affor
    1.57
     bandung
    1.56
     maneu
    1.55
     accla
    1.54
     unlaw
    1.53
     jaya
    1.53
     reluct
    1.51
    Act Density 0.027%

    No Known Activations