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

    Neuronpedia

    INDEX
    Explanations

    key statistical terms and indicators related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alars
    -0.18
    bens
    -0.17
    cctor
    -0.16
    .scalablytyped
    -0.16
    setDisplay
    -0.15
    oplevel
    -0.15
    lluminate
    -0.15
    amburger
    -0.15
    orre
    -0.15
    >manual
    -0.15
    POSITIVE LOGITS
    rate
    0.16
    pline
    0.15
    dat
    0.15
    emu
    0.14
     Belle
    0.14
    iale
    0.14
     Aware
    0.14
    .ca
    0.14
     Bund
    0.13
     CÆ¡
    0.13
    Act Density 0.046%

    No Known Activations