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

    Neuronpedia

    INDEX
    Explanations

    sections detailing updates and changes in software features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.43
     ་་
    -1.42
     itſelf
    -1.40
    findpost
    -1.39
     Monfieur
    -1.36
     myſelf
    -1.36
     doubtnut
    -1.30
     greateſt
    -1.30
     Jefus
    -1.29
     auffi
    -1.27
    POSITIVE LOGITS
    </h2>
    0.89
    </strong>
    0.86
     I
    0.80
    …
    0.79
     ‘
    0.78
     
    0.76
    </b>
    0.76
     the
    0.74
     in
    0.73
     …
    0.73
    Act Density 0.165%

    No Known Activations