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

    Neuronpedia

    INDEX
    Explanations

    text contributions to reports

    oai_token-act-pair · gpt-3.5-turbo

    elements pertaining to journalistic contributions and authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mods
    -0.81
    é¾įå¥ij士
    -0.77
     Majesty
    -0.73
    stones
    -0.68
    AppData
    -0.68
     peers
    -0.68
     horr
    -0.63
    cum
    -0.62
     mete
    -0.61
     disadvant
    -0.58
    POSITIVE LOGITS
    inion
    0.92
     Coverage
    0.72
    cerpt
    0.70
    anamo
    0.68
    swick
    0.67
     VIDE
    0.67
     contributed
    0.66
    enhagen
    0.66
    acas
    0.66
    olicy
    0.63
    Act Density 0.094%

    No Known Activations