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

    Neuronpedia

    INDEX
    Explanations

    evidence and references to support claims or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -1.10
    تقاوى
    -0.87
     ujednoznacz
    -0.86
     MainAxisSize
    -0.84
    Хьажоргаш
    -0.82
    MENAFN
    -0.81
    StoryboardSegue
    -0.80
     متعلقه
    -0.79
    
    -0.78
     betweenstory
    -0.78
    POSITIVE LOGITS
     evidenced
    0.46
     manifested
    0.42
     signs
    0.39
    lich
    0.39
    ме
    0.39
    сти
    0.38
     indicated
    0.38
    me
    0.38
     fatto
    0.37
    asgi
    0.37
    Act Density 0.669%

    No Known Activations