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

    Neuronpedia

    INDEX
    Explanations

    computer-generated text formatting commands

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols used in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bengal
    -0.70
     board
    -0.69
     library
    -0.68
     Bris
    -0.66
     Droid
    -0.64
     Sapphire
    -0.62
     blanket
    -0.62
     detached
    -0.62
     playbook
    -0.61
     fid
    -0.61
    POSITIVE LOGITS
    Ĵ
    1.32
    ¹
    1.26
    ª
    1.24
    IJ
    1.21
    ı
    1.19
    ł
    1.17
    ij
    1.15
    «
    1.11
    ³
    1.10
    Į
    1.08
    Act Density 0.157%

    No Known Activations