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

    Neuronpedia

    INDEX
    Explanations

    positive evaluations of experiences or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    crement
    -0.14
    Decor
    -0.14
     hero
    -0.14
     heroes
    -0.14
    été
    -0.13
    Certain
    -0.13
     certain
    -0.13
     Decor
    -0.13
     epis
    -0.13
    اÙĤ
    -0.13
    POSITIVE LOGITS
    à¹Ģลย
    0.19
     overall
    0.18
    overall
    0.17
    istrovstvÃŃ
    0.15
     indeed
    0.15
     although
    0.14
    ">//
    0.14
    GMEM
    0.14
     getView
    0.13
    ophy
    0.13
    Act Density 0.196%

    No Known Activations