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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "There" at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "there" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Throne
    -0.68
     Ashes
    -0.62
     IPM
    -0.61
     apex
    -0.61
     evils
    -0.57
     Coffin
    -0.56
     Slayer
    -0.56
     nib
    -0.55
     oats
    -0.54
     Coat
    -0.54
    POSITIVE LOGITS
    abouts
    1.45
    after
    1.17
    upon
    1.11
     were
    1.06
     are
    1.01
     weren
    1.00
    fore
    0.93
    FORE
    0.93
     was
    0.92
    zbollah
    0.89
    Act Density 0.107%

    No Known Activations