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

    Neuronpedia

    INDEX
    Explanations

    elements related to conflict, targeting, and the influence of deceitful forces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orney
    -0.16
    .loads
    -0.15
    shint
    -0.15
    ctp
    -0.15
    ÙĪÙĦد
    -0.14
    lah
    -0.14
    ubat
    -0.14
    Ø´Ùĩ
    -0.13
    à¥įश
    -0.13
    quent
    -0.13
    POSITIVE LOGITS
    idar
    0.18
    asco
    0.17
    idia
    0.16
    oky
    0.16
    alm
    0.15
    ochrome
    0.14
    steller
    0.14
    ãĥ¼ãĥ«
    0.14
     rein
    0.14
     Gle
    0.14
    Act Density 0.305%

    No Known Activations