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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or formatting indicators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.84
      
    -0.83
     
    -0.68
     The
    -0.67
     -
    -0.63
    -0.63
     A
    -0.63
       
    -0.60
    ↵↵
    -0.60
        
    -0.58
    POSITIVE LOGITS
    يميديا
    0.83
     AttributeSet
    0.75
    ThroughAttribute
    0.72
     Baillargeon
    0.69
     Wikimedijinoj
    0.69
     mohair
    0.68
     Exactos
    0.68
     endwhile
    0.67
     aggro
    0.66
    octanol
    0.64
    Act Density 0.328%

    No Known Activations