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

    Neuronpedia

    INDEX
    Explanations

    the word "too" as an indication of addition or agreement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "too."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plurality
    -0.64
    icipated
    -0.58
    estamp
    -0.57
     overflow
    -0.57
    payer
    -0.56
     Volks
    -0.54
     Hamm
    -0.53
     impossibility
    -0.53
     Hammond
    -0.53
     Canaver
    -0.52
    POSITIVE LOGITS
     :)
    0.87
    !:
    0.85
    !
    0.80
    .<
    0.80
    !.
    0.77
     ;)
    0.77
    .,
    0.77
     ðŁĻĤ
    0.76
     much
    0.76
     :-)
    0.76
    Act Density 0.027%

    No Known Activations