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

    Neuronpedia

    INDEX
    Explanations

    possessive phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate enumeration or listing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gans
    -0.71
    ardless
    -0.67
    oided
    -0.64
    onz
    -0.63
    heading
    -0.63
     alone
    -0.62
     arrives
    -0.60
    etermination
    -0.60
    plot
    -0.60
    igion
    -0.59
    POSITIVE LOGITS
     noteworthy
    1.07
     notable
    1.04
     highlights
    0.85
     recent
    0.85
     interesting
    0.84
     famous
    0.81
     memorable
    0.80
     favorite
    0.80
     fascinating
    0.80
     pertinent
    0.78
    Act Density 0.123%

    No Known Activations