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

    Neuronpedia

    INDEX
    Explanations

    technical terms or jargon

    oai_token-act-pair · gpt-3.5-turbo

    references to specific terms and their meanings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Depths
    -0.70
    âĹ¼
    -0.68
    artney
    -0.67
    ©¶æ¥µ
    -0.66
    hurst
    -0.66
    jriwal
    -0.65
     choir
    -0.64
    ¥ŀ
    -0.62
     Bagg
    -0.62
     Hills
    -0.62
    POSITIVE LOGITS
     coined
    1.00
    ifier
    0.99
     interchange
    0.91
    icide
    0.86
    ified
    0.84
    ifiers
    0.84
    ology
    0.80
    paces
    0.80
    ification
    0.80
    sworth
    0.77
    Act Density 0.038%

    No Known Activations