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

    Neuronpedia

    INDEX
    Explanations

    references to the current condition or status of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "state," particularly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    poons
    -0.84
    enic
    -0.80
    sites
    -0.79
     Carbuncle
    -0.77
    odi
    -0.75
    iffe
    -0.74
     Torn
    -0.73
    peria
    -0.67
    esi
    -0.67
    edin
    -0.66
    POSITIVE LOGITS
    lessness
    0.98
     quo
    0.97
    less
    0.96
    fulness
    0.88
    LESS
    0.88
    liness
    0.87
     legislatures
    0.86
    ful
    0.86
    manship
    0.85
    room
    0.85
    Act Density 0.045%

    No Known Activations