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

    Neuronpedia

    INDEX
    Explanations

    non-English characters or special characters, specifically the letter "š"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     semblance
    -0.71
    rage
    -0.63
     Karma
    -0.61
     gy
    -0.61
     fundamentals
    -0.59
     fu
    -0.58
     Ghosts
    -0.58
     seismic
    -0.58
     Chinatown
    -0.58
     revolutionary
    -0.58
    POSITIVE LOGITS
    Å¡
    2.28
     Matthews
    1.64
     Samp
    1.63
     Hew
    1.33
     coached
    1.32
    batch
    1.24
    ł
    1.08
     Bain
    0.92
    Leaks
    0.90
     Philipp
    0.87
    Act Density 0.024%

    No Known Activations