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

    Neuronpedia

    INDEX
    Explanations

    titles or names starting with "The"

    oai_token-act-pair · gpt-3.5-turbo

    the end of a text or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     patiently
    -0.74
    perse
    -0.72
    lished
    -0.70
     according
    -0.69
     partake
    -0.68
    ement
    -0.68
    poke
    -0.67
     undergo
    -0.65
     endeav
    -0.65
     contributed
    -0.65
    POSITIVE LOGITS
    atre
    1.16
    oret
    1.15
    resa
    1.07
    ories
    1.02
     Simpsons
    1.01
    sis
    0.97
    mes
    0.96
     Basics
    0.96
    orem
    0.93
     Beatles
    0.90
    Act Density 0.150%

    No Known Activations