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

    Neuronpedia

    INDEX
    Explanations

    references to educational and administrative titles or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ún
    -0.20
     ná»Ńa
    -0.15
    /mail
    -0.15
    üçük
    -0.14
    oris
    -0.14
    ób
    -0.14
    deniz
    -0.14
    éĨ´
    -0.14
    emple
    -0.14
    ingly
    -0.14
    POSITIVE LOGITS
    ate
    0.16
     Emer
    0.15
     himself
    0.15
    ëĭĺ
    0.15
    reek
    0.14
    call
    0.14
    rup
    0.14
    smouth
    0.14
    ship
    0.14
     yyn
    0.14
    Act Density 0.119%

    No Known Activations