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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to conflict and strategic decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zek
    -0.16
    ÌĨ
    -0.15
    kili
    -0.15
    mlin
    -0.15
    oday
    -0.15
     infix
    -0.15
    ifix
    -0.14
    uset
    -0.14
     ØŃاÙĦØ©
    -0.14
    ç£
    -0.14
    POSITIVE LOGITS
    izzo
    0.16
    iswa
    0.15
    umen
    0.15
    ihat
    0.15
    ibel
    0.14
     Soul
    0.14
    ughter
    0.14
    (klass
    0.14
     blanc
    0.14
     Blanc
    0.14
    Act Density 0.012%

    No Known Activations