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

    Neuronpedia

    INDEX
    Explanations

    system status messages and error codes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    -
    -0.59
     to
    -0.57
     G
    -0.56
     -
    -0.56
     —
    -0.53
    .
    -0.52
     zu
    -0.52
     ${
    -0.52
    kom
    -0.52
     zag
    -0.52
    POSITIVE LOGITS
    +#+
    1.85
     myſelf
    1.31
     itſelf
    1.29
     doubtnut
    1.20
     pleaſure
    1.13
     ་་
    1.10
     Anſ
    1.09
     Jefus
    1.08
     للاسماء
    1.08
     ſind
    1.06
    Act Density 0.875%

    No Known Activations