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

    Neuronpedia

    INDEX
    Explanations

    asterisks (*)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the asterisk symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unification
    -0.68
     seiz
    -0.66
    è¡
    -0.65
     manif
    -0.64
     shaping
    -0.64
     travers
    -0.64
    inator
    -0.64
     migr
    -0.63
    ivated
    -0.63
    etheless
    -0.62
    POSITIVE LOGITS
    AUT
    0.88
    Names
    0.83
     Required
    0.81
    NEW
    0.80
    TON
    0.79
    Correction
    0.78
    CM
    0.77
    NB
    0.77
    Thompson
    0.76
    NOTE
    0.73
    Act Density 0.028%

    No Known Activations