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

    Neuronpedia

    INDEX
    Explanations

    words related to materials or substances

    oai_token-act-pair · gpt-3.5-turbo

    references to various styles and forms of artistic or aesthetic expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WARN
    -0.77
    ajor
    -0.76
    INESS
    -0.74
    女
    -0.72
     Miko
    -0.72
    izen
    -0.70
    ITNESS
    -0.69
    animous
    -0.66
    nesota
    -0.66
     Immunity
    -0.65
    POSITIVE LOGITS
    sty
    1.30
    les
    0.88
    led
    0.86
    rous
    0.82
    lers
    0.81
    rene
    0.81
    aky
    0.80
     Sty
    0.80
    gian
    0.79
    rator
    0.78
    Act Density 0.014%

    No Known Activations