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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating limitations or exclusivity of actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isd
    -0.17
     reklam
    -0.16
    aa
    -0.16
    ĺ
    -0.15
    tt
    -0.15
    romise
    -0.15
    rieve
    -0.14
    yp
    -0.14
    ÏĦά
    -0.14
    .readValue
    -0.14
    POSITIVE LOGITS
    zen
    0.16
    imat
    0.15
     fon
    0.15
    838
    0.14
    compatible
    0.14
    सर
    0.14
    ultz
    0.14
     Burgess
    0.14
    ignon
    0.14
    etroit
    0.13
    Act Density 0.065%

    No Known Activations