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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending in a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     helper
    -0.78
     asylum
    -0.74
     salute
    -0.72
    interstitial
    -0.72
     allowance
    -0.71
     panc
    -0.70
     inner
    -0.69
     hourly
    -0.69
     tyr
    -0.68
     dich
    -0.65
    POSITIVE LOGITS
     Alternatively
    1.49
     Ideally
    1.38
     Regardless
    1.37
     Otherwise
    1.37
     Perhaps
    1.31
     Certainly
    1.30
     Depending
    1.29
     Especially
    1.28
     Instead
    1.28
     Either
    1.27
    Act Density 0.716%

    No Known Activations