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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intentions or plans

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intention or future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DAQ
    -0.64
     Parables
    -0.63
    isted
    -0.62
    cius
    -0.62
    oran
    -0.61
     Belt
    -0.60
    ventional
    -0.58
     quo
    -0.56
    DNA
    -0.56
     Sporting
    -0.55
    POSITIVE LOGITS
     be
    1.06
     never
    0.93
    ĸļ
    0.93
     eventually
    0.86
     someday
    0.83
     unleash
    0.80
     soon
    0.80
    soon
    0.80
    aido
    0.78
    never
    0.78
    Act Density 0.229%

    No Known Activations