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

    Neuronpedia

    INDEX
    Explanations

    negative connotations and criticisms related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kdo
    -0.15
     NÄĽm
    -0.14
    italize
    -0.14
    isser
    -0.13
    ltk
    -0.13
    nek
    -0.13
    ừng
    -0.13
     shove
    -0.13
    èIJ¥ä¸ļ
    -0.13
    agli
    -0.12
    POSITIVE LOGITS
    éné
    0.15
    retty
    0.14
     Ced
    0.14
    !..
    0.13
    /null
    0.13
    oad
    0.13
    -than
    0.13
    ãĥ¼ãĥ¬
    0.13
    ohl
    0.12
    IX
    0.12
    Act Density 0.368%

    No Known Activations