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

    Neuronpedia

    INDEX
    Explanations

    specific sequences of characters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific symbol or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     metic
    -0.69
     Lumpur
    -0.69
     messing
    -0.65
     bund
    -0.63
     nuts
    -0.62
    querque
    -0.61
     obj
    -0.61
    omorphic
    -0.61
     tur
    -0.61
     creep
    -0.60
    POSITIVE LOGITS
    feat
    1.12
    requ
    1.08
    while
    1.03
    where
    1.01
    should
    0.97
    stru
    0.97
    inducing
    0.95
    enough
    0.93
    once
    0.93
    among
    0.93
    Act Density 0.024%

    No Known Activations