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

    Neuronpedia

    INDEX
    Explanations

    references to current and former roles or statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocos
    -0.19
     Various
    -0.16
    erli
    -0.15
    uria
    -0.15
     various
    -0.15
    iped
    -0.14
    /MM
    -0.14
    ưỡng
    -0.14
    ihn
    -0.14
    rello
    -0.14
    POSITIVE LOGITS
    uale
    0.16
    oser
    0.15
     hrd
    0.15
    ament
    0.14
    telegram
    0.14
     Sloan
    0.14
    PEC
    0.13
    antis
    0.13
    enor
    0.13
    üçük
    0.13
    Act Density 0.156%

    No Known Activations