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

    Neuronpedia

    INDEX
    Explanations

    evaluations of actions or events that are negative or transformative in nature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĦÛĮÙĩ
    -0.16
    λία
    -0.15
     EITHER
    -0.15
    Mixin
    -0.14
     пÑĢедваÑĢ
    -0.14
    neath
    -0.14
     оÑĩеÑĢед
    -0.14
     Credits
    -0.14
    UIApplication
    -0.14
    agar
    -0.13
    POSITIVE LOGITS
     downright
    0.50
     outright
    0.49
     border
    0.29
     actual
    0.28
     flat
    0.26
     altogether
    0.26
     actually
    0.25
     entirely
    0.25
     actively
    0.24
     plain
    0.23
    Act Density 0.224%

    No Known Activations