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

    Neuronpedia

    INDEX
    Explanations

    words related to side effects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to side effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESCO
    -0.86
    issance
    -0.81
    ãĤ¼ãĤ¦ãĤ¹
    -0.76
    essors
    -0.75
    Ĥİ
    -0.75
    iott
    -0.74
    uracy
    -0.73
    æ©Ł
    -0.73
    ãģ®éŃĶ
    -0.72
    shire
    -0.71
    POSITIVE LOGITS
    kick
    1.03
    side
    0.90
    burn
    0.82
    board
    0.78
    bars
    0.78
     ups
    0.78
     Side
    0.77
     lobe
    0.75
    bill
    0.74
     side
    0.74
    Act Density 0.027%

    No Known Activations