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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific measurement and analytical processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     am
    -0.57
    .
    -0.54
    ↵
    -0.52
     C
    -0.49
     D
    -0.48
     se
    -0.47
     F
    -0.46
    cadilly
    -0.46
    <eos>
    -0.45
     d
    -0.45
    POSITIVE LOGITS
     myſelf
    0.97
     صوتيه
    0.96
     ſeveral
    0.93
     Diſ
    0.92
     Efq
    0.92
     Theſe
    0.92
     himſelf
    0.91
     Anſ
    0.90
     Reſ
    0.88
     Eſ
    0.86
    Act Density 0.278%

    No Known Activations