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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or likelihood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ches
    -0.58
     kullanılır
    -0.50
     voeten
    -0.50
    D
    -0.50
     iris
    -0.49
    єм
    -0.49
    an
    -0.49
    S
    -0.48
     inginkan
    -0.48
    R
    -0.48
    POSITIVE LOGITS
     probably
    2.04
     Probably
    2.01
    Probably
    1.86
    probably
    1.83
     prolly
    1.74
     likely
    1.57
     Likely
    1.48
     probablemente
    1.46
    bably
    1.43
     probable
    1.41
    Act Density 0.084%

    No Known Activations