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

    Neuronpedia

    INDEX
    Explanations

    dialogue involving physical actions and spatial descriptions

    oai_token-act-pair · gpt-3.5-turbo

    actions and reactions conveyed through body language and gestures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.80
    osate
    -0.79
    glers
    -0.78
    Reviewer
    -0.74
     ingred
    -0.71
    indal
    -0.70
    halla
    -0.69
    ouls
    -0.68
    oÄŁ
    -0.67
    cair
    -0.67
    POSITIVE LOGITS
     nervously
    0.92
     grin
    0.90
     impatient
    0.86
     nodded
    0.82
     expression
    0.81
     smiled
    0.81
     reassuring
    0.80
     apolog
    0.80
     smile
    0.79
     softly
    0.78
    Act Density 0.313%

    No Known Activations