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

    Neuronpedia

    INDEX
    Explanations

    instances of capitalized words and significant numeric values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
      
    -0.72
     
    -0.71
    las
    -0.58
    -
    -0.57
     “
    -0.56
    ”,
    -0.56
        
    -0.55
     –
    -0.55
    ”
    -0.55
     on
    -0.55
    POSITIVE LOGITS
     дописавши
    1.54
     Roskov
    1.49
     autorytatywna
    1.27
    Datuak
    1.20
    rungsseite
    1.18
    istoitu
    1.09
    AndEndTag
    1.08
    bewerken
    1.07
     للمعارف
    1.07
    ValueStyle
    1.06
    Act Density 0.369%

    No Known Activations