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

    Neuronpedia

    INDEX
    Explanations

    references to characters in a story

    oai_token-act-pair · gpt-3.5-turbo

    mentions of characters in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¿½
    -0.75
    sterdam
    -0.71
    ntil
    -0.69
    aband
    -0.69
    ת
    -0.68
    ateurs
    -0.66
    ackers
    -0.66
    obar
    -0.65
    rup
    -0.65
    roxy
    -0.65
    POSITIVE LOGITS
    acters
    1.48
    istically
    1.13
    istics
    1.05
     arcs
    0.95
     characters
    0.91
     Characters
    0.88
    izations
    0.88
     portray
    0.85
     portrayed
    0.81
     inhab
    0.80
    Act Density 0.044%

    No Known Activations