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

    Neuronpedia

    INDEX
    Explanations

    technical terms and references related to academic or research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agher
    -0.17
     DAC
    -0.16
     Tags
    -0.15
    igans
    -0.15
    aget
    -0.15
    usters
    -0.14
     Pew
    -0.14
    íĴį
    -0.14
    DAC
    -0.14
    uckles
    -0.14
    POSITIVE LOGITS
     arreglo
    0.15
    ç¯
    0.14
    .xhtml
    0.14
    ÙĤرار
    0.13
     زÙĪج
    0.13
    HING
    0.13
     ADVISED
    0.13
    UBE
    0.13
    ALSE
    0.12
    _READONLY
    0.12
    Act Density 0.002%

    No Known Activations