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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "terrible" and related negative descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fty
    -0.17
    zend
    -0.15
    ordial
    -0.15
    ernity
    -0.15
     ticking
    -0.15
    ogn
    -0.14
    osomal
    -0.14
     Bout
    -0.14
    ÑĤоÑİ
    -0.13
    apping
    -0.13
    POSITIVE LOGITS
    acha
    0.19
    ÑĢеÑħ
    0.16
    uger
    0.15
    stm
    0.15
    rams
    0.14
    kov
    0.14
    glm
    0.14
    leo
    0.14
    Ùħز
    0.14
    acho
    0.14
    Act Density 0.013%

    No Known Activations