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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation marks and quotation marks within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.55
    Picture
    -0.55
     picture
    -0.54
     محفوظة
    -0.53
    DOCTYPE
    -0.52
    '}';
    -0.52
     InputDecoration
    -0.49
    EndTag
    -0.48
     Picture
    -0.47
    #
    -0.47
    POSITIVE LOGITS
     itſelf
    0.79
     myſelf
    0.75
     ſche
    0.69
     Diſ
    0.68
     fubject
    0.67
     Jefus
    0.67
    expandindo
    0.64
     himſelf
    0.64
    ftagPool
    0.63
     themſelves
    0.63
    Act Density 0.068%

    No Known Activations