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

    Neuronpedia

    INDEX
    Explanations

    prepositions, particularly "of" and "on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
      
    -0.69
     
    -0.61
       
    -0.55
     for
    -0.54
        
    -0.53
    si
    -0.48
     a
    -0.48
    /
    -0.46
     has
    -0.45
    ↵
    -0.45
    POSITIVE LOGITS
     Efq
    1.00
    niająca
    0.99
    دانشنامهٔ
    0.98
    AndEndTag
    0.96
     tartalomajánló
    0.93
    NUMX
    0.93
    شهاد
    0.92
    ^(@)
    0.92
     itſelf
    0.90
     $_(
    0.89
    Act Density 0.937%

    No Known Activations