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

    Neuronpedia

    INDEX
    Explanations

    expressions related to probabilities or future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hin
    -0.17
     olab
    -0.16
    òn
    -0.16
     Sometimes
    -0.15
    sometimes
    -0.15
    gregar
    -0.15
     sometimes
    -0.14
    ÙĨÙĩ
    -0.14
     вообÑīе
    -0.14
    ometimes
    -0.14
    POSITIVE LOGITS
     likely
    0.98
     probably
    0.86
    likely
    0.84
     Likely
    0.78
    probably
    0.76
     Probably
    0.71
    Probably
    0.68
     probable
    0.68
     most
    0.64
     likelihood
    0.54
    Act Density 0.655%

    No Known Activations