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

    Neuronpedia

    INDEX
    Explanations

    phrases that express positive evaluations or assessments of people, objects, or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umb
    -0.17
    تÙĩا
    -0.16
    znik
    -0.16
    anter
    -0.15
    urname
    -0.15
    arra
    -0.15
    .MixedReality
    -0.14
     Gast
    -0.14
    横
    -0.14
    amina
    -0.14
    POSITIVE LOGITS
    uhn
    0.18
    é®
    0.16
    .af
    0.14
    æģ©
    0.14
    azı
    0.14
    iture
    0.13
    _DIRECT
    0.13
     tol
    0.13
    395
    0.13
    iterals
    0.13
    Act Density 0.117%

    No Known Activations