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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe qualities or characteristics of objects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocab
    -0.15
    Ø·ÙĬ
    -0.14
    stÃŃ
    -0.14
    ibr
    -0.14
    SKTOP
    -0.14
     probation
    -0.14
    ocht
    -0.13
    ORMAL
    -0.13
     *</
    -0.13
    arters
    -0.13
    POSITIVE LOGITS
    edin
    0.16
    à¹Ģย
    0.16
    ae
    0.14
    ķĮ
    0.14
     ÐŁÑĢод
    0.14
    æŃ©
    0.14
    rog
    0.14
    low
    0.14
    enheim
    0.14
     Depths
    0.13
    Act Density 0.213%

    No Known Activations