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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating poor quality or negative experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lij
    -0.17
    shaw
    -0.15
     Rooney
    -0.14
    jiang
    -0.14
    aternion
    -0.14
    roupe
    -0.14
    arLayout
    -0.14
    (equalTo
    -0.14
    agoon
    -0.14
    oppel
    -0.13
    POSITIVE LOGITS
     Diss
    0.16
    åIJIJ
    0.15
     gran
    0.14
    vap
    0.14
     Lev
    0.14
    orde
    0.14
    eryl
    0.14
     available
    0.14
     spd
    0.14
     partition
    0.14
    Act Density 0.492%

    No Known Activations