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

    Neuronpedia

    INDEX
    Explanations

    references to "CS" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to specific championships or competitions in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    runner
    -0.66
    ously
    -0.65
     thous
    -0.63
     unaccompanied
    -0.62
    judicial
    -0.62
     bour
    -0.62
     publicity
    -0.62
    accompan
    -0.61
    selves
    -0.61
    ishi
    -0.60
    POSITIVE LOGITS
    IRO
    1.02
    ANE
    0.95
    HT
    0.87
    OME
    0.86
    OOL
    0.85
    DP
    0.84
    ession
    0.83
    ettings
    0.81
    helle
    0.81
    HD
    0.80
    Act Density 0.008%

    No Known Activations