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

    Neuronpedia

    INDEX
    Explanations

    negative contractions related to denial or inability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ofs
    -0.17
    ilim
    -0.16
    ancode
    -0.16
    otch
    -0.15
    oss
    -0.14
    avou
    -0.14
    hy
    -0.14
    nder
    -0.14
    вÑĸ
    -0.14
    angement
    -0.14
    POSITIVE LOGITS
     anymore
    0.18
    iced
    0.17
     necessarily
    0.16
    theless
    0.15
     even
    0.15
    ched
    0.14
    icol
    0.14
    listed
    0.14
    kup
    0.14
    kus
    0.14
    Act Density 0.058%

    No Known Activations