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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "final."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Stephenson
    -0.66
     Vel
    -0.61
    pris
    -0.59
    endam
    -0.54
     C
    -0.52
    füllung
    -0.52
     nationaux
    -0.52
     cortos
    -0.51
    .*,
    -0.51
     domésticos
    -0.51
    POSITIVE LOGITS
    Спасылкі
    0.79
     PFA
    0.76
     betweenstory
    0.74
    parsedMessage
    0.73
    tableFuture
    0.71
    anyahu
    0.70
    KURZBESCHREIBUNG
    0.70
    IntoConstraints
    0.68
     Kome
    0.67
    jgl
    0.66
    Act Density 0.001%

    No Known Activations