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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events involving breaking up something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to breaking or separating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hunts
    -0.63
    ait
    -0.62
    WHERE
    -0.62
     projecting
    -0.61
     Boxing
    -0.61
    gee
    -0.60
    tto
    -0.59
    velop
    -0.59
    READ
    -0.59
    anwhile
    -0.58
    POSITIVE LOGITS
    river
    0.95
    arity
    0.81
    rates
    0.78
    dates
    0.75
    glomer
    0.74
    stocks
    0.73
    rate
    0.73
    scenes
    0.72
    stock
    0.70
    rations
    0.68
    Act Density 0.028%

    No Known Activations