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

    Neuronpedia

    INDEX
    Explanations

    speculative statements or possibilities indicated by the word "that" followed by a verb or noun

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ãĥīãĥ©
    -0.82
    ario
    -0.71
    verend
    -0.70
    ãĤ´
    -0.70
    apsed
    -0.69
    olphin
    -0.66
    83
    -0.66
    arest
    -0.66
    ãĥĸ
    -0.65
    Rated
    -0.65
    POSITIVE LOGITS
     maybe
    0.95
     perhaps
    0.87
    might
    0.86
     hint
    0.84
     possibly
    0.84
     possibility
    0.79
     motives
    0.78
    perhaps
    0.77
    maybe
    0.76
     speculate
    0.75
    Act Density 0.261%

    No Known Activations