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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the act of stating, reporting, or communicating information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    calar
    -0.16
    allery
    -0.15
    roti
    -0.15
    lector
    -0.15
    _DECLARE
    -0.15
    iciel
    -0.14
    atos
    -0.14
    ONTAL
    -0.14
    okino
    -0.14
    .scalablytyped
    -0.14
    POSITIVE LOGITS
     Core
    0.15
    amet
    0.15
    697
    0.15
    lamaz
    0.15
    UPLE
    0.15
    kers
    0.14
     discre
    0.14
    zed
    0.13
    ates
    0.13
    ortho
    0.13
    Act Density 0.045%

    No Known Activations