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

    Neuronpedia

    INDEX
    Explanations

    corrections or errors within text

    oai_token-act-pair · gpt-3.5-turbo

    corrections or amendments to previously stated information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uries
    -0.80
    ãĤ¼ãĤ¦ãĤ¹
    -0.78
    thood
    -0.77
    luaj
    -0.74
    iors
    -0.72
    ocious
    -0.71
    æ©
    -0.71
    çļ
    -0.70
    soDeliveryDate
    -0.69
    aceae
    -0.68
    POSITIVE LOGITS
     typo
    1.03
     deleted
    1.01
     incorrectly
    0.97
     incorrect
    0.97
     revised
    0.88
     formatting
    0.86
     *)
    0.85
     mistakenly
    0.85
     inaccur
    0.85
     omitted
    0.84
    Act Density 0.321%

    No Known Activations