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

    Neuronpedia

    INDEX
    Explanations

    the word "that" preceded by certain words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istics
    -0.74
     Mane
    -0.73
    oby
    -0.71
     Leilan
    -0.70
    ciples
    -0.66
    orah
    -0.66
    Ľ
    -0.65
    hens
    -0.64
    IDES
    -0.64
    pps
    -0.62
    POSITIVE LOGITS
     pesky
    1.21
     kind
    0.93
     same
    0.91
     fateful
    0.87
     sort
    0.82
    interstitial
    0.79
     particular
    0.78
     nifty
    0.78
     type
    0.78
    same
    0.75
    Act Density 0.208%

    No Known Activations