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

    Neuronpedia

    INDEX
    Explanations

    report headings or subject lines

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Roskov
    -1.15
    ValueStyle
    -0.81
     kaarangay
    -0.77
    aarrggbb
    -0.70
     beginnetje
    -0.70
    AutoScale
    -0.70
    يكب
    -0.70
    ThroughAttribute
    -0.70
    matchCondition
    -0.69
    AutoScaleMode
    -0.69
    POSITIVE LOGITS
    </b>
    0.52
     don
    0.51
    亨
    0.50
     Inter
    0.49
     [
    0.49
     -
    0.48
     .
    0.48
     R
    0.47
     ...
    0.46
     Don
    0.45
    Act Density 0.003%

    No Known Activations