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

    Neuronpedia

    INDEX
    Explanations

    rhetorical questions or phrases that imply agreement or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    conversational phrases that seek agreement or validation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.64
    ounters
    -0.60
     Foods
    -0.60
    ounter
    -0.59
    ifax
    -0.58
    ilogy
    -0.57
    hetti
    -0.56
    esa
    -0.56
    quished
    -0.55
    irting
    -0.55
    POSITIVE LOGITS
    kay
    0.95
    cause
    0.91
     eh
    0.81
     ya
    0.78
     traveller
    0.76
     sir
    0.76
     huh
    0.73
     mortal
    0.73
    ?).
    0.67
    kie
    0.66
    Act Density 0.203%

    No Known Activations