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

    Neuronpedia

    INDEX
    Explanations

    phrases within brackets

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a punctuation mark

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jah
    -0.84
    imates
    -0.77
    ãĥIJ
    -0.77
    ilion
    -0.76
    =-=-=-=-=-=-=-=-
    -0.72
    ÙĴ
    -0.70
    thur
    -0.69
    isen
    -0.69
    rael
    -0.68
    omorphic
    -0.68
    POSITIVE LOGITS
     Anyway
    0.81
     Likewise
    0.79
     Similarly
    0.78
     Moreover
    0.73
     externalToEVAOnly
    0.71
     Conversely
    0.71
     Modes
    0.70
     Instead
    0.70
     srfAttach
    0.70
     Nevertheless
    0.70
    Act Density 0.034%

    No Known Activations