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

    Neuronpedia

    INDEX
    Explanations

    words that convey a sense of dissatisfaction or negative emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bol
    -0.16
    elim
    -0.15
    -library
    -0.14
    shal
    -0.14
    Ìģc
    -0.14
    \grid
    -0.14
    elop
    -0.13
     ÑģпÑĢави
    -0.13
    aldi
    -0.13
    anzi
    -0.13
    POSITIVE LOGITS
    覧
    0.15
    еÑĢÑĪ
    0.15
    yal
    0.14
    ı
    0.14
    avel
    0.13
    mainwindow
    0.13
    jang
    0.13
    vetica
    0.13
     è¾
    0.13
     ÃĦ
    0.12
    Act Density 0.487%

    No Known Activations