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

    Neuronpedia

    INDEX
    Explanations

    probability-related phrases and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ches
    -0.65
    D
    -0.62
     Z
    -0.62
    R
    -0.60
    an
    -0.59
    on
    -0.57
    at
    -0.56
    Z
    -0.55
    –
    -0.53
     D
    -0.53
    POSITIVE LOGITS
     Probably
    1.66
     probably
    1.63
     prolly
    1.55
    Probably
    1.51
    probably
    1.47
    bably
    1.42
     likely
    1.35
     Likely
    1.26
     probablemente
    1.18
     Probable
    1.17
    Act Density 0.089%

    No Known Activations