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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the initiation or establishment of something significant or influential

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating initiation or establishment of events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vised
    -0.72
    ividual
    -0.68
    ith
    -0.66
    cles
    -0.64
    regate
    -0.64
    ignty
    -0.61
    ocations
    -0.60
     endeav
    -0.60
    ifice
    -0.60
    abilities
    -0.60
    POSITIVE LOGITS
     precedent
    0.97
     tongues
    0.94
     sail
    0.89
    tle
    0.89
     preced
    0.86
     abl
    0.78
    flame
    0.77
     jaws
    0.76
     sails
    0.73
     fires
    0.73
    Act Density 0.071%

    No Known Activations