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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to taking action or making decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bohem
    -0.85
    eger
    -0.73
     Rath
    -0.66
     spat
    -0.65
     vigorously
    -0.65
     Kok
    -0.62
     thirst
    -0.62
     privately
    -0.62
    geist
    -0.61
     nort
    -0.60
    POSITIVE LOGITS
    taker
    0.95
    ahead
    0.95
    tale
    0.88
    your
    0.88
    luster
    0.88
    away
    0.85
    aways
    0.84
    up
    0.83
    ety
    0.82
    release
    0.82
    Act Density 0.070%

    No Known Activations