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

    Neuronpedia

    INDEX
    Explanations

    key moments of physical interaction and pauses in dialogue

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.79
    AutoScale
    -0.79
     whoſe
    -0.79
     Efq
    -0.79
     مشين
    -0.78
     uſed
    -0.78
    WebVitals
    -0.77
     Jefus
    -0.77
     OFDb
    -0.77
     itſelf
    -0.75
    POSITIVE LOGITS
     stop
    0.70
     STOP
    0.68
     Stop
    0.66
     stops
    0.65
    Stops
    0.57
    STOP
    0.56
    Stop
    0.56
     Stops
    0.54
     stopping
    0.53
    stop
    0.51
    Act Density 0.039%

    No Known Activations