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

    Neuronpedia

    INDEX
    Explanations

    ASCII art of various shapes

    oai_token-act-pair · gpt-3.5-turbo

    vertical bar symbols and other graphic characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beir
    -0.79
    rons
    -0.78
    ory
    -0.74
    alis
    -0.74
    ancies
    -0.73
    anium
    -0.71
    oday
    -0.70
     Canaver
    -0.70
    ĸļ
    -0.70
    enance
    -0.69
    POSITIVE LOGITS
    cffff
    1.00
     |--
    0.95
    ··
    0.90
    cffffcc
    0.86
    ËĪ
    0.82
     grep
    0.81
     +---
    0.76
    ¯¯¯¯¯¯¯¯
    0.75
    ¯¯
    0.73
    λ
    0.72
    Act Density 0.012%

    No Known Activations