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

    Neuronpedia

    INDEX
    Explanations

    expressions that indicate exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mum
    -0.16
    AGMA
    -0.15
    ÑĤим
    -0.15
     Pil
    -0.15
    stial
    -0.14
     alb
    -0.14
     Ron
    -0.14
     Firm
    -0.14
    OLA
    -0.14
    Broad
    -0.13
    POSITIVE LOGITS
    ä¹İ
    0.16
     noreferrer
    0.15
    enso
    0.14
     Accred
    0.14
    restricted
    0.14
    773
    0.14
    islav
    0.14
     sey
    0.14
    ži
    0.14
    bad
    0.14
    Act Density 0.070%

    No Known Activations