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

    Neuronpedia

    INDEX
    Explanations

    descriptions or comparisons of experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing subjective experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.79
    phabet
    -0.69
    luster
    -0.69
    ukong
    -0.65
    ãĥĩãĤ£
    -0.65
    \\\\\\\\
    -0.64
    andise
    -0.62
    artifacts
    -0.61
    Americ
    -0.61
    Winner
    -0.61
    POSITIVE LOGITS
     to
    0.73
     raining
    0.72
    tical
    0.63
     everyday
    0.63
    icult
    0.61
     ta
    0.59
     psychologically
    0.58
     folly
    0.57
     uphill
    0.55
     aliens
    0.55
    Act Density 0.132%

    No Known Activations