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

    Neuronpedia

    INDEX
    Explanations

    mentions of characters in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to characters in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yg
    -0.74
    VERTIS
    -0.71
    rup
    -0.70
    ctr
    -0.65
    isco
    -0.64
     Tant
    -0.64
    ¿½
    -0.63
    atories
    -0.63
    alm
    -0.63
    LOCK
    -0.62
    POSITIVE LOGITS
    acters
    1.47
    istically
    1.12
    istics
    1.04
     assassinate
    0.86
    izations
    0.85
     characters
    0.84
     arcs
    0.80
     portraits
    0.79
    isations
    0.78
     Characters
    0.76
    Act Density 0.039%

    No Known Activations