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

    Neuronpedia

    INDEX
    Explanations

    references to specific authors or contributors in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.90
    UnusedPrivate
    -0.88
     pleaſure
    -0.86
     myſelf
    -0.81
     perſon
    -0.80
    ſelf
    -0.79
    AsyncResult
    -0.76
    存于互联网档案馆
    -0.75
    abestanden
    -0.73
     Majefty
    -0.72
    POSITIVE LOGITS
     labelled
    0.71
     labeled
    0.70
     simple
    0.67
    labelled
    0.66
     labeling
    0.65
     labelling
    0.63
     label
    0.62
    labeled
    0.62
     tag
    0.57
     Zhang
    0.57
    Act Density 0.132%

    No Known Activations