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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to emotional expression

    oai_token-act-pair · gpt-3.5-turbo

    terms related to emotional expression and societal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.72
    azo
    -0.70
    onga
    -0.67
    INS
    -0.66
    ANS
    -0.64
     Italians
    -0.64
     Garry
    -0.63
     Accuracy
    -0.63
     Viet
    -0.63
     Khe
    -0.62
    POSITIVE LOGITS
     outward
    1.13
     inward
    1.07
    ly
    0.83
    ward
    0.81
    heastern
    0.79
    worldly
    0.77
    robe
    0.76
    comings
    0.75
    angular
    0.74
    selves
    0.74
    Act Density 0.005%

    No Known Activations