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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aleza
    -0.15
    (optional
    -0.15
    YD
    -0.15
    ãİ¡
    -0.14
    anguard
    -0.14
    yg
    -0.14
    anz
    -0.14
    nothrow
    -0.13
    ilon
    -0.13
    èĮĤ
    -0.13
    POSITIVE LOGITS
     likely
    0.59
    likely
    0.52
     lik
    0.50
     probable
    0.50
     likelihood
    0.49
     Likely
    0.46
     unlikely
    0.46
     probability
    0.43
     probably
    0.43
     probabilities
    0.40
    Act Density 0.141%

    No Known Activations