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

    Neuronpedia

    INDEX
    Explanations

    the word "Actually" within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "Actually" along with its variations, indicating a focus on corrections or affirmations in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pending
    -0.77
     potential
    -0.72
     spirits
    -0.63
     runners
    -0.62
     consistent
    -0.61
     sweep
    -0.61
     continuing
    -0.61
     across
    -0.61
     players
    -0.61
     pinpoint
    -0.61
    POSITIVE LOGITS
     Actually
    3.12
    Actually
    2.49
    actually
    1.75
     Anyway
    1.67
     Really
    1.58
     Apparently
    1.51
     Probably
    1.46
     Somehow
    1.43
     Honestly
    1.42
     Basically
    1.37
    Act Density 0.027%

    No Known Activations