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

    Neuronpedia

    INDEX
    Explanations

    key concepts and terms related to regulations and standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    era
    -0.17
    atus
    -0.16
    uming
    -0.15
    ERA
    -0.15
     moto
    -0.14
    xx
    -0.14
    uty
    -0.14
    inal
    -0.14
     Joint
    -0.14
     scrut
    -0.14
    POSITIVE LOGITS
     Pru
    0.17
    ampton
    0.16
    .Butter
    0.14
    _UPPER
    0.14
    yre
    0.14
    serrat
    0.14
    leanup
    0.14
    !=(
    0.14
     fed
    0.14
    ROL
    0.14
    Act Density 0.001%

    No Known Activations