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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific references within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grade
    -0.16
    Looper
    -0.15
    ATUS
    -0.15
    apot
    -0.15
    agh
    -0.14
     ÐĽÑĥÑĩ
    -0.14
    /cgi
    -0.14
    ouce
    -0.14
    atum
    -0.14
    _cov
    -0.14
    POSITIVE LOGITS
    Ñıл
    0.16
     stil
    0.15
    лÑıд
    0.14
     Commerce
    0.14
    uhn
    0.14
     Shoe
    0.14
     punct
    0.14
    niÄį
    0.14
    gings
    0.14
    ër
    0.14
    Act Density 0.011%

    No Known Activations