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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or speculation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of conjecture or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    taboola
    -0.78
     Antar
    -0.74
    contained
    -0.72
    rupulous
    -0.72
    interrupted
    -0.71
    iterranean
    -0.70
    aples
    -0.68
     contiguous
    -0.68
    Bio
    -0.65
    ctic
    -0.65
    POSITIVE LOGITS
     guesses
    1.01
     guess
    0.89
     guessing
    0.84
    ariat
    0.82
     guessed
    0.77
    llor
    0.75
     incorrectly
    0.75
     Guess
    0.73
    lessly
    0.73
    oti
    0.73
    Act Density 0.021%

    No Known Activations