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

    Neuronpedia

    INDEX
    Explanations

    references to academic institutions and related research publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulas
    -0.17
     gent
    -0.14
    ach
    -0.14
    ONUS
    -0.14
    ousse
    -0.14
    lassian
    -0.14
    oreach
    -0.14
     Rut
    -0.14
     said
    -0.13
    ous
    -0.13
    POSITIVE LOGITS
     INTERRUPTION
    0.16
    μή
    0.15
    uve
    0.14
    nosis
    0.14
    SSERT
    0.14
    venta
    0.14
    awy
    0.14
    ruc
    0.14
    AZE
    0.14
    inition
    0.13
    Act Density 0.002%

    No Known Activations