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

    Neuronpedia

    INDEX
    Explanations

    terms related to rankings and awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gue
    -0.18
     Liv
    -0.16
    uluk
    -0.15
    ç·Ĵ
    -0.15
     ell
    -0.15
     Her
    -0.15
    iani
    -0.14
     Verb
    -0.14
    zem
    -0.14
    als
    -0.14
    POSITIVE LOGITS
    igon
    0.17
    िà¤Ń
    0.14
     Daw
    0.14
    /plugin
    0.14
    avior
    0.14
    raÄį
    0.14
    young
    0.14
    anco
    0.14
     %↵↵
    0.14
    بØŃ
    0.13
    Act Density 0.101%

    No Known Activations