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

    Neuronpedia

    INDEX
    Explanations

    mentions of compliance or adherence in a technical or legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldi
    -0.22
    .createClass
    -0.18
    ĥ
    -0.16
    ÄĽ
    -0.16
    lichkeit
    -0.15
    gle
    -0.15
    VELO
    -0.15
    rippling
    -0.15
     addCriterion
    -0.14
    ovah
    -0.14
    POSITIVE LOGITS
     Sw
    0.15
     nests
    0.15
     va
    0.14
    åĸĦ
    0.14
     suff
    0.14
    dump
    0.14
    idal
    0.13
    0.13
    196
    0.13
    ç½®
    0.13
    Act Density 0.007%

    No Known Activations