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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional complexity and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.17
     nin
    -0.16
    adlo
    -0.15
    ugu
    -0.15
    _EXPECT
    -0.15
    ktion
    -0.15
    stin
    -0.14
    positories
    -0.14
     Kushner
    -0.14
     Baz
    -0.14
    POSITIVE LOGITS
    лиÑħ
    0.16
    ruh
    0.16
     enough
    0.15
    ruž
    0.14
    783
    0.14
    AE
    0.14
    ruc
    0.14
    uluk
    0.14
    irth
    0.13
    lung
    0.13
    Act Density 0.276%

    No Known Activations