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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and expressions of identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isposable
    -0.18
    oret
    -0.17
    ırak
    -0.17
    ete
    -0.16
    SB
    -0.15
    arges
    -0.15
    etti
    -0.15
    atas
    -0.15
    iry
    -0.14
    itized
    -0.14
    POSITIVE LOGITS
    OMP
    0.17
    ilan
    0.17
    _Params
    0.16
    ìŀIJìĿ¸
    0.16
    tps
    0.16
    angan
    0.15
    428
    0.14
    _lng
    0.14
     spl
    0.13
    312
    0.13
    Act Density 0.155%

    No Known Activations