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

    Neuronpedia

    INDEX
    Explanations

    quotes, attributions, and statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "was" indicating significant statements or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !'
    -0.66
    ··
    -0.64
    !'"
    -0.62
    ?'
    -0.59
    ress
    -0.58
     Battles
    -0.58
    ?'"
    -0.58
     Quarter
    -0.57
    .'
    -0.56
     Vers
    -0.56
    POSITIVE LOGITS
     "...
    1.07
     "
    1.03
     "âĢ¦
    1.01
     "[
    0.96
     "'
    0.87
     ''
    0.87
     unlikely
    0.87
     "#
    0.85
     indeed
    0.84
     akin
    0.82
    Act Density 0.423%

    No Known Activations