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

    Neuronpedia

    INDEX
    Explanations

    references to armed groups and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĨاÙħ
    -0.17
    ảo
    -0.16
    elfast
    -0.16
    æª
    -0.15
    boom
    -0.15
    gether
    -0.15
     pul
    -0.15
    ỡ
    -0.15
    pty
    -0.14
    innen
    -0.14
    POSITIVE LOGITS
    ζί
    0.16
    linger
    0.15
    idel
    0.15
    mith
    0.15
    ivec
    0.15
    Ĥ¬
    0.15
    aket
    0.15
    .$.
    0.14
    nit
    0.14
     Bend
    0.14
    Act Density 0.016%

    No Known Activations