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

    Neuronpedia

    INDEX
    Explanations

    special characters that may indicate emotions or emphasis like arrows and emojis

    oai_token-act-pair · gpt-3.5-turbo

    sequences of characters resembling special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scatter
    -0.63
     buggy
    -0.62
     rooting
    -0.62
     guiActiveUnfocused
    -0.60
     scattering
    -0.60
     lodging
    -0.60
     bread
    -0.59
     smokes
    -0.58
     Sakuya
    -0.58
     rubbish
    -0.58
    POSITIVE LOGITS
    ¹
    1.00
    £
    0.94
    âĸº
    0.94
    ı
    0.90
    º
    0.89
    »
    0.87
    ¡
    0.86
    §
    0.84
    Į
    0.84
    į
    0.83
    Act Density 0.425%

    No Known Activations