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

    Neuronpedia

    INDEX
    Explanations

    phrases related to probabilities and likelihoods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bourgoin
    -0.85
     Efq
    -0.78
    WEBPACK
    -0.77
     StatelessWidget
    -0.76
    NSS
    -0.75
     Theſe
    -0.73
     Anſ
    -0.71
     Reſ
    -0.71
     Familienname
    -0.70
    ագրություններ
    -0.69
    POSITIVE LOGITS
     chances
    1.23
     likelihood
    1.12
     probability
    1.06
    probability
    1.06
     probab
    1.03
     likely
    1.03
    Likelihood
    1.03
    likelihood
    1.03
     chance
    1.03
     Chances
    1.02
    Act Density 0.303%

    No Known Activations