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

    Neuronpedia

    INDEX
    Explanations

    sentences with declarations or statements of truth

    oai_token-act-pair · gpt-3.5-turbo

    statements affirming a particular truth or reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stad
    -0.75
    assetsadobe
    -0.74
    rador
    -0.71
    eor
    -0.65
    iterranean
    -0.62
    andise
    -0.62
    inventoryQuantity
    -0.60
    throp
    -0.60
    allic
    -0.59
    effic
    -0.59
    POSITIVE LOGITS
     that
    1.09
     THAT
    0.98
    that
    0.77
     nobody
    0.77
     undeniable
    0.73
     none
    0.72
     simple
    0.71
    ,
    0.70
    adays
    0.70
     we
    0.70
    Act Density 0.084%

    No Known Activations