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

    Neuronpedia

    INDEX
    Explanations

    expressions related to dieting and food choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ¬
    -0.15
     ê³µëıĻ
    -0.14
    pins
    -0.14
    è¿«
    -0.13
    upertino
    -0.13
    unar
    -0.13
    hangi
    -0.13
    ante
    -0.13
     bore
    -0.13
    urnished
    -0.13
    POSITIVE LOGITS
     temptation
    0.16
     tempt
    0.15
     Nev
    0.15
    .lv
    0.14
     Blob
    0.14
    ép
    0.14
    ipar
    0.14
     sed
    0.14
    ifest
    0.14
    irma
    0.13
    Act Density 0.140%

    No Known Activations