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

    Neuronpedia

    INDEX
    Explanations

    references to characters within text

    oai_token-act-pair · gpt-3.5-turbo

    references to character design or traits in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĸ¹
    -0.73
    ynthesis
    -0.70
    yip
    -0.69
    arcity
    -0.66
    kaya
    -0.63
    akening
    -0.61
    Accessory
    -0.60
    allows
    -0.59
    aughters
    -0.59
    owers
    -0.59
    POSITIVE LOGITS
     char
    0.99
    acters
    0.96
    itably
    0.95
    quer
    0.79
    ret
    0.78
    lie
    0.76
    \\\\\\\\
    0.76
    coon
    0.75
    isma
    0.75
    rette
    0.74
    Act Density 0.006%

    No Known Activations