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

    Neuronpedia

    INDEX
    Explanations

    instances of specific prefixes or roots in words, particularly related to social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.58
     V
    -0.48
    -
    -0.47
     п
    -0.47
     full
    -0.45
     lo
    -0.44
     health
    -0.44
     bi
    -0.43
    +
    -0.43
     types
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    1.36
    GEBURTSDATUM
    1.02
     خارجية
    1.02
    يكب
    0.91
    SharedCtor
    0.89
    </thead>
    0.87
     InputDecoration
    0.86
     оригіналу
    0.86
     ModelExpression
    0.86
     itſelf
    0.86
    Act Density 0.158%

    No Known Activations