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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umably
    -0.68
    */(
    -0.64
     Anyway
    -0.61
     Presumably
    -0.60
     filler
    -0.59
    ausible
    -0.59
    edit
    -0.59
     Predict
    -0.58
    udo
    -0.58
     Worse
    -0.58
    POSITIVE LOGITS
     compassionate
    0.91
     courageous
    0.91
     dignity
    0.87
     wonderful
    0.87
     sacrific
    0.86
    cellence
    0.84
     compassion
    0.83
     courage
    0.81
     heartfelt
    0.81
     grateful
    0.80
    Act Density 1.275%

    No Known Activations