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

    Neuronpedia

    INDEX
    Explanations

    references to approval and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ìģc
    -0.15
    輪
    -0.14
    uckets
    -0.14
    oÅĪ
    -0.14
    utex
    -0.14
    infeld
    -0.13
    abby
    -0.13
    quential
    -0.13
    ç«ł
    -0.13
    lj
    -0.13
    POSITIVE LOGITS
    eland
    0.14
    cxx
    0.13
     Ashe
    0.13
     Giang
    0.12
    jÃŃm
    0.12
     nÄĽho
    0.12
    leftright
    0.12
    etc
    0.12
     çĽ
    0.12
    gmail
    0.11
    Act Density 0.053%

    No Known Activations