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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing possibilities or hypothetical situations

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases indicating possibility or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oric
    -0.85
    rett
    -0.72
    */(
    -0.65
    cedented
    -0.65
    uctor
    -0.64
     Dragonbound
    -0.64
     Enforcement
    -0.63
     Completed
    -0.63
    scar
    -0.62
    cies
    -0.62
    POSITIVE LOGITS
     someday
    0.97
     conce
    0.94
    haps
    0.93
     plaus
    0.89
     feas
    0.89
     be
    0.82
    iest
    0.82
     tremend
    0.82
     theoretically
    0.80
    ily
    0.79
    Act Density 0.037%

    No Known Activations