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

    Neuronpedia

    INDEX
    Explanations

    references to manipulation or superficial actions that serve to enhance one's image or brand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     true
    -0.15
     quality
    -0.14
    unda
    -0.14
     clear
    -0.14
     limit
    -0.14
    羣æŃ£
    -0.14
     informed
    -0.13
     proper
    -0.13
     plain
    -0.13
     fully
    -0.13
    POSITIVE LOGITS
     convenient
    0.22
     Convenient
    0.21
     Convenience
    0.17
     pleasing
    0.17
     convenience
    0.17
     conveniently
    0.17
    ickle
    0.15
     Appe
    0.15
    æ°ı
    0.15
     íݸ
    0.15
    Act Density 0.489%

    No Known Activations