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

    Neuronpedia

    INDEX
    Explanations

    words that indicate an evaluation or assessment of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing opinions or subjective impressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apsed
    -0.75
    isin
    -0.73
    jac
    -0.71
    keyes
    -0.69
    aredevil
    -0.68
    uve
    -0.68
    pour
    -0.66
    aign
    -0.66
    cot
    -0.66
    gart
    -0.66
    POSITIVE LOGITS
     louder
    0.91
     vaguely
    0.88
     awfully
    0.86
     suspic
    0.83
     like
    0.80
    bite
    0.80
     omin
    0.79
     familiar
    0.79
     snipp
    0.79
     faintly
    0.78
    Act Density 0.023%

    No Known Activations