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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of a phrase indicating a casual or informal future action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     weakened
    -0.65
     Healthy
    -0.61
     Detection
    -0.59
     weakening
    -0.59
     Ferry
    -0.57
     Barn
    -0.57
     SAR
    -0.57
     ATI
    -0.57
    lished
    -0.56
    quickShipAvailable
    -0.56
    POSITIVE LOGITS
    uminati
    1.34
     be
    0.95
     NEVER
    0.93
    inois
    0.92
    never
    0.83
    know
    0.81
    initely
    0.78
    rieve
    0.78
     never
    0.77
     gladly
    0.77
    Act Density 0.033%

    No Known Activations