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

    Neuronpedia

    INDEX
    Explanations

    specific characters used as markers or indicators

    oai_token-act-pair · gpt-3.5-turbo

    instances of certain non-standard characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     buggy
    -0.75
     decomp
    -0.74
     collecting
    -0.74
     coast
    -0.73
     minim
    -0.73
     capsule
    -0.72
     floating
    -0.69
     downs
    -0.68
    itably
    -0.68
     shrouded
    -0.68
    POSITIVE LOGITS
    ONSORED
    0.99
    £
    0.98
    ¹
    0.87
    ĸļ
    0.86
    ł
    0.86
     Ibid
    0.83
    º
    0.80
    catentry
    0.80
    Order
    0.80
    ¯
    0.80
    Act Density 0.209%

    No Known Activations