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

    Neuronpedia

    INDEX
    Explanations

    the word "mostly" and its variations, indicating an emphasis on predominant characteristics or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llib
    -0.17
    Ñıж
    -0.16
    weit
    -0.15
    atter
    -0.15
    icl
    -0.14
    antar
    -0.14
    anga
    -0.14
    dj
    -0.13
    orra
    -0.13
    wers
    -0.13
    POSITIVE LOGITS
    .vn
    0.15
     importantly
    0.14
    uyá»ĩt
    0.14
     newPassword
    0.14
    elden
    0.14
    hetto
    0.13
     же
    0.13
    üstü
    0.13
    seg
    0.13
     à¹Ĩ
    0.13
    Act Density 0.008%

    No Known Activations