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

    Neuronpedia

    INDEX
    Explanations

    instances of the character "Ċ" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.11
    2:0.03
    3:0.10
    4:0.07
    5:0.08
    6:0.04
    7:0.07
    8:0.09
    9:0.02
    10:0.06
    11:0.25
    Negative Logits
    ­
    -4.86
     —
    -4.35
     ­
    -4.06
     ―
    -3.99
     …
    -3.70
    ADVERTISEMENT
    -3.49
    ——
    -3.32
    —
    -3.11
    —-
    -3.09
    ,)
    -3.06
    POSITIVE LOGITS
     ",
    4.12
    ",
    3.90
            
    3.58
    ".
    3.50
      
    3.46
    !".
    3.40
       
    3.31
    ?",
    3.26
        
    3.25
    !",
    3.24
    Act Density 0.002%

    No Known Activations