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

    Neuronpedia

    INDEX
    Explanations

    references to future plans or potential scenarios

    oai_token-act-pair · gpt-3.5-turbo

    terms related to planning and forecasting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idy
    -0.80
    idious
    -0.79
    girl
    -0.73
    killer
    -0.72
    aceae
    -0.69
    ivari
    -0.68
     Alph
    -0.68
    unin
    -0.67
    lain
    -0.66
    lyss
    -0.65
    POSITIVE LOGITS
    hower
    0.77
    urations
    0.75
    pty
    0.75
    Ń·
    0.74
    ãĤº
    0.73
    ãĤ¤ãĥĪ
    0.70
    ãĥĥãĤ¯
    0.70
    ational
    0.70
    æĪ¦
    0.69
    andum
    0.68
    Act Density 0.068%

    No Known Activations