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

    Neuronpedia

    INDEX
    Explanations

    expressions of self-confidence and assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ward
    -0.19
    ependency
    -0.17
    aul
    -0.17
    ternal
    -0.15
    ::<
    -0.15
    WARD
    -0.14
    endar
    -0.14
    uman
    -0.14
     WaitForSeconds
    -0.14
    ephy
    -0.14
    POSITIVE LOGITS
    /conf
    0.19
     confidence
    0.18
    /power
    0.17
    éc
    0.16
     Confidence
    0.16
    ably
    0.15
     Guerr
    0.14
    jez
    0.14
     confident
    0.14
    رÛĮب
    0.13
    Act Density 0.024%

    No Known Activations