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

    Neuronpedia

    INDEX
    Explanations

    facts or statements presented as truth

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "the fact" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arms
    -0.77
     Klux
    -0.74
     throats
    -0.72
    avorite
    -0.71
    Interstitial
    -0.66
    artney
    -0.65
    crow
    -0.64
    sung
    -0.63
    airs
    -0.63
     chambers
    -0.62
    POSITIVE LOGITS
    ional
    1.06
    ually
    1.00
    Fact
    0.96
    uality
    0.92
     fact
    0.88
     Fact
    0.86
    icity
    0.86
    orial
    0.84
    itious
    0.84
    undo
    0.76
    Act Density 0.028%

    No Known Activations