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

    Neuronpedia

    INDEX
    Explanations

    regular expression patterns

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     "
    -0.52
    MathML
    -0.50
    </b>
    -0.50
     in
    -0.49
     “
    -0.49
     search
    -0.49
     stop
    -0.49
    <eos>
    -0.48
     U
    -0.48
    InteropServices
    -0.48
    POSITIVE LOGITS
     étoit
    0.97
     /\.(
    0.97
     zelve
    0.95
     pouvoit
    0.94
     itſelf
    0.93
     myſelf
    0.92
     auroit
    0.92
     avoient
    0.91
     /\.
    0.91
    Gambas
    0.91
    Act Density 0.004%

    No Known Activations