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

    Neuronpedia

    INDEX
    Explanations

    references to the second-person perspective in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annon
    -0.15
    lum
    -0.15
    abee
    -0.15
    สà¸Ķ
    -0.15
     Zum
    -0.15
    onaut
    -0.14
    Smoke
    -0.14
    اءة
    -0.14
    ë°±
    -0.14
    esel
    -0.14
    POSITIVE LOGITS
     Iron
    0.14
    stru
    0.14
    صÙĩ
    0.14
    andr
    0.14
    uke
    0.14
    itan
    0.13
    essler
    0.13
     bagi
    0.13
    ukes
    0.13
    è¿
    0.13
    Act Density 0.425%

    No Known Activations