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

    Neuronpedia

    INDEX
    Explanations

    facts or statements that are particularly important or noteworthy

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the phrase "the fact" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.86
    wana
    -0.72
    airs
    -0.69
    itsch
    -0.69
    asca
    -0.66
    iverpool
    -0.63
    ESE
    -0.63
    artney
    -0.62
    annis
    -0.61
     livest
    -0.61
    POSITIVE LOGITS
    ually
    1.14
    uality
    1.13
    ional
    1.07
    orial
    1.02
    uate
    0.84
    itious
    0.81
    oids
    0.79
    uation
    0.78
    uated
    0.77
    uates
    0.75
    Act Density 0.025%

    No Known Activations