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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing certainty and knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pis
    -0.14
    IDEOS
    -0.14
    اÙĦا
    -0.14
    igest
    -0.14
    βά
    -0.14
    _RS
    -0.14
    ular
    -0.14
    uplicated
    -0.14
    _ABI
    -0.14
    dbContext
    -0.13
    POSITIVE LOGITS
     certainty
    0.65
     sure
    0.65
     Sure
    0.54
    sure
    0.53
     confidence
    0.48
    Sure
    0.46
     confident
    0.42
     ÑĥвеÑĢ
    0.41
    SURE
    0.41
     cert
    0.40
    Act Density 0.328%

    No Known Activations