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

    Neuronpedia

    INDEX
    Explanations

    Slavic or Russian language characters and names

    oai_token-act-pair · gpt-3.5-turbo

    repeated characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berman
    -1.14
    ulative
    -0.86
    legate
    -0.83
    ulatory
    -0.76
    utations
    -0.75
    builders
    -0.72
    emetery
    -0.71
    pees
    -0.71
    bers
    -0.70
    ierrez
    -0.70
    POSITIVE LOGITS
    \\\\\\\\
    0.81
    heartedly
    0.77
    CHAPTER
    0.73
     Monstrous
    0.70
    onso
    0.69
    ī
    0.69
    \\\\\\\\\\\\\\\\
    0.69
    osis
    0.66
    yy
    0.66
     Unable
    0.66
    Act Density 0.014%

    No Known Activations