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

    Neuronpedia

    INDEX
    Explanations

    complex interactions between people and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    奪
    -0.16
    Ī¬
    -0.15
    pios
    -0.15
    itorio
    -0.15
    Kill
    -0.14
    ubu
    -0.14
     seedu
    -0.14
    yla
    -0.14
    itori
    -0.14
    860
    -0.14
    POSITIVE LOGITS
    被
    0.42
    éģŃ
    0.37
     被
    0.36
     being
    0.35
    åıĹåĪ°
    0.33
     bá»ĭ
    0.32
    åıĹ
    0.31
     zosta
    0.30
    being
    0.29
     receive
    0.28
    Act Density 0.277%

    No Known Activations