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

    Neuronpedia

    INDEX
    Explanations

    contractions or possessives

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate certainty or factual statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.71
    oire
    -0.66
    osate
    -0.66
     Supports
    -0.65
     Gutenberg
    -0.64
    è¦ļéĨĴ
    -0.63
    orie
    -0.63
    ibus
    -0.62
    =>
    -0.61
    FTWARE
    -0.61
    POSITIVE LOGITS
     nonetheless
    1.66
     nevertheless
    1.57
     still
    1.19
     also
    1.19
     undeniably
    1.07
    still
    1.04
     hardly
    1.04
     equally
    1.03
     ALSO
    1.03
    etheless
    1.01
    Act Density 0.231%

    No Known Activations