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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical locations

    oai_token-act-pair · gpt-3.5-turbo

    specific sound patterns or phonetic elements in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chwitz
    -0.88
    RF
    -0.77
    ãĥ¯ãĥ³
    -0.74
    Qual
    -0.74
    Weather
    -0.71
     Amend
    -0.71
    lik
    -0.69
    Ju
    -0.67
    Market
    -0.67
     Shank
    -0.67
    POSITIVE LOGITS
    ously
    0.84
    acters
    0.81
    SHIP
    0.79
     flourish
    0.77
    aneously
    0.75
    rosis
    0.72
    ingly
    0.72
    attering
    0.70
    heric
    0.70
    anship
    0.69
    Act Density 0.328%

    No Known Activations