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

    Neuronpedia

    INDEX
    Explanations

    expressions related to variations and degrees of characteristics or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wiki
    -0.17
    wil
    -0.16
    emple
    -0.15
    Wil
    -0.15
     Nap
    -0.15
    oyer
    -0.15
    unker
    -0.15
    ooke
    -0.15
    .CSS
    -0.15
    SSIP
    -0.15
    POSITIVE LOGITS
    ur
    0.16
     depending
    0.15
    dp
    0.14
    chal
    0.14
     Tro
    0.14
     fortunes
    0.13
     fortune
    0.13
    alah
    0.13
    ypad
    0.13
    oro
    0.13
    Act Density 0.264%

    No Known Activations