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

    Neuronpedia

    INDEX
    Explanations

    words related to common or usual things

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "typical" or "normal" characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heed
    -0.76
    appointed
    -0.72
    enced
    -0.70
    acus
    -0.69
    nuts
    -0.66
    rencies
    -0.65
    mentation
    -0.65
    Tickets
    -0.65
    aughter
    -0.64
    arching
    -0.64
    POSITIVE LOGITS
     fare
    0.86
     americ
    0.82
     weekday
    0.81
     sized
    0.81
     deviation
    0.81
    typ
    0.80
     American
    0.79
    ized
    0.78
     Western
    0.78
     western
    0.77
    Act Density 0.072%

    No Known Activations