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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and negations related to consequences or lack thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.63
     oprot
    -0.62
    CPtr
    -0.59
    StructEnd
    -0.58
    ähren
    -0.55
    NameInMap
    -0.54
    kura
    -0.52
    μμ
    -0.52
    Демографія
    -0.52
    Ac
    -0.52
    POSITIVE LOGITS
     überhaupt
    1.52
     вообще
    1.35
     vůbec
    1.27
     ogóle
    1.23
     altogether
    1.08
     even
    0.90
     вовсе
    0.88
     affatto
    0.88
     whatsoever
    0.82
     اصلا
    0.81
    Act Density 0.459%

    No Known Activations