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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions that convey embarrassment or self-consciousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©
    -0.17
    lander
    -0.15
    angered
    -0.15
     Coverage
    -0.15
    辺
    -0.14
    NO
    -0.14
    igmat
    -0.14
    743
    -0.14
    odo
    -0.14
    echa
    -0.14
    POSITIVE LOGITS
     ç
    0.16
    rack
    0.15
    bson
    0.15
    vore
    0.14
    ivan
    0.14
    crest
    0.14
    èĴĤ
    0.14
    division
    0.14
    getattr
    0.14
    upp
    0.13
    Act Density 0.104%

    No Known Activations