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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating troublesome situations or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    statements or comments that conclude with punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.78
     disembark
    -0.76
     prepar
    -0.74
     haul
    -0.72
     earthqu
    -0.72
    arbon
    -0.72
    urther
    -0.71
     pione
    -0.71
     emanc
    -0.70
    yond
    -0.70
    POSITIVE LOGITS
     Sometimes
    1.48
     Hence
    1.32
     Therefore
    1.32
     Often
    1.31
     Luckily
    1.31
     That
    1.27
     Thus
    1.25
     Usually
    1.25
     Thankfully
    1.22
     Fortunately
    1.22
    Act Density 0.487%

    No Known Activations