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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new paragraphs or sections in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.81
      
    -0.75
     I
    -0.75
     on
    -0.71
     M
    -0.71
     “
    -0.70
     (
    -0.69
    ,
    -0.68
     ‘
    -0.68
    </strong>
    -0.67
    POSITIVE LOGITS
    ſelves
    1.34
     myſelf
    1.34
     itſelf
    1.32
     Efq
    1.30
     ་་
    1.29
    findpost
    1.28
     Majefty
    1.27
     Anſ
    1.26
     ―――――
    1.25
     purpoſe
    1.22
    Act Density 0.015%

    No Known Activations