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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns and terms related to organizations and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.71
    OGND
    -0.65
    ValueStyle
    -0.62
    Халык
    -0.62
    SequentialGroup
    -0.58
    AddTagHelper
    -0.56
     Houſe
    -0.54
     فريبيس
    -0.53
     îng
    -0.52
     ErrIntOverflow
    -0.50
    POSITIVE LOGITS
     Romanian
    0.52
    änien
    0.48
    criminator
    0.44
    nezeu
    0.42
    RetentionPolicy
    0.42
    NAM
    0.38
     Clever
    0.38
     Invocation
    0.37
    вила
    0.37
     introduces
    0.37
    Act Density 0.057%

    No Known Activations