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

    Neuronpedia

    INDEX
    Explanations

    patterns of repetition in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.74
     myſelf
    -1.72
     ―――――
    -1.60
     Monfieur
    -1.56
     doubtnut
    -1.55
     themſelves
    -1.53
     Theſe
    -1.49
     Jefus
    -1.46
     becauſe
    -1.45
     Anſ
    -1.44
    POSITIVE LOGITS
    </strong>
    0.82
     (
    0.80
    .
    0.79
     I
    0.79
    </b>
    0.79
     c
    0.76
     M
    0.76
     and
    0.75
     G
    0.75
     C
    0.74
    Act Density 0.350%

    No Known Activations