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

    Neuronpedia

    INDEX
    Explanations

    words related to criticism or strong disapproval

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "rebuke" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.81
     Kafka
    -0.72
     à¨
    -0.71
    âĢ¢âĢ¢
    -0.71
     Valhalla
    -0.69
     Monaco
    -0.65
     Inquisitor
    -0.63
    meal
    -0.62
     Grail
    -0.62
     Sons
    -0.61
    POSITIVE LOGITS
    ounding
    1.17
    ounded
    1.07
    uffed
    1.05
    anche
    1.03
    uked
    0.99
    uls
    0.95
    aul
    0.94
    oll
    0.93
    ukes
    0.92
    acked
    0.92
    Act Density 0.011%

    No Known Activations