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

    Neuronpedia

    INDEX
    Explanations

    symbols and miscellanea in different writing styles

    oai_token-act-pair · gpt-3.5-turbo

    unique or special characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Learns
    -0.79
     metic
    -0.65
     Carbuncle
    -0.62
     behavi
    -0.61
     litter
    -0.60
    kson
    -0.59
     Kills
    -0.58
    glers
    -0.58
     Pool
    -0.58
     hemor
    -0.57
    POSITIVE LOGITS
    =~=~
    0.70
    AppData
    0.68
    âĸł
    0.68
    finished
    0.67
    CLOSE
    0.65
     denotes
    0.65
    cffffcc
    0.65
    Ïī
    0.64
    Ult
    0.63
    _>
    0.62
    Act Density 0.148%

    No Known Activations