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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation, particularly ones related to questions and mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥ŀ
    -0.90
    monton
    -0.79
    undai
    -0.77
    ocr
    -0.75
    iscopal
    -0.74
    outheastern
    -0.74
    deen
    -0.72
    elaide
    -0.71
    iren
    -0.71
    opolis
    -0.71
    POSITIVE LOGITS
     crates
    0.72
     Crate
    0.66
     Pledge
    0.63
     exclus
    0.62
    armor
    0.61
     Recipes
    0.61
     crate
    0.60
     discounted
    0.60
     Fav
    0.59
     Valentine
    0.59
    Act Density 0.014%

    No Known Activations