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

    Neuronpedia

    INDEX
    Explanations

    references to character attributes or abilities in a gaming context

    oai_token-act-pair · gpt-3.5-turbo

    references to characters in games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yg
    -0.85
    IED
    -0.77
    اÙĦ
    -0.73
    agles
    -0.72
    lar
    -0.71
    è¦
    -0.71
    ת
    -0.69
    ven
    -0.69
    omatic
    -0.68
    vid
    -0.68
    POSITIVE LOGITS
    acters
    1.44
    istics
    1.35
    istically
    1.11
    izations
    0.89
    izes
    0.76
    istic
    0.75
    isations
    0.74
     charact
    0.73
     sheet
    0.73
     customization
    0.72
    Act Density 0.019%

    No Known Activations