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

    Neuronpedia

    INDEX
    Explanations

    phrases related to probability or likelihood

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to chances or probabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minus
    -0.87
    culated
    -0.81
    ahime
    -0.81
     ILCS
    -0.80
    zek
    -0.79
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.79
    umbers
    -0.79
    geist
    -0.78
    umbered
    -0.78
    chool
    -0.73
    POSITIVE LOGITS
     success
    1.36
     succeeding
    1.33
     encountering
    1.31
     obtaining
    1.26
     winning
    1.23
     finding
    1.23
     achieving
    1.22
     catching
    1.19
     survival
    1.18
     surviving
    1.18
    Act Density 0.157%

    No Known Activations