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

    Neuronpedia

    INDEX
    Explanations

    action-oriented verbs and references to decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rega
    -0.15
    kan
    -0.15
     ones
    -0.15
     function
    -0.14
     steps
    -0.14
    andin
    -0.14
    adin
    -0.14
    issan
    -0.14
     functions
    -0.13
    872
    -0.13
    POSITIVE LOGITS
    ENCH
    0.17
     Tato
    0.15
    idders
    0.15
    лади
    0.15
    ibaba
    0.15
    еÑģÑĤ
    0.15
    RuleContext
    0.15
    hů
    0.15
    pread
    0.14
    ÑĮÑı
    0.14
    Act Density 0.005%

    No Known Activations