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

    Neuronpedia

    INDEX
    Explanations

    the repeated occurrence of the word "that" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" and its variations, indicating a focus on references to particular ideas or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ľ
    -0.76
    istics
    -0.75
    ciples
    -0.73
    uously
    -0.68
    \\\\\\\\
    -0.68
    isers
    -0.68
    rior
    -0.68
    hens
    -0.67
    wear
    -0.66
    aries
    -0.66
    POSITIVE LOGITS
     pesky
    1.28
     same
    0.92
     kind
    0.90
     fateful
    0.90
     particular
    0.87
     elusive
    0.84
     nifty
    0.84
     sort
    0.82
     sucker
    0.81
    interstitial
    0.78
    Act Density 0.157%

    No Known Activations