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

    Neuronpedia

    INDEX
    Explanations

    content that contains significant numerical or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.01
     poffe
    -0.93
     himſelf
    -0.93
     diſt
    -0.90
     myſelf
    -0.89
     ſta
    -0.88
     raiſ
    -0.87
     Majefty
    -0.86
     uſ
    -0.86
     itſelf
    -0.85
    POSITIVE LOGITS
     (
    0.51
    UrlResolution
    0.50
    C
    0.42
     T
    0.42
     -
    0.40
    <em>
    0.40
    <eos>
    0.40
    BeginContext
    0.40
     at
    0.40
    -
    0.39
    Act Density 0.036%

    No Known Activations