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

    Neuronpedia

    INDEX
    Explanations

    words related to multiples or repeated actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "triple" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbm
    -0.87
    ä½ľ
    -0.73
    alach
    -0.69
    enegger
    -0.68
    swer
    -0.67
    eared
    -0.67
    earing
    -0.67
    ihil
    -0.67
    netflix
    -0.65
    perse
    -0.64
    POSITIVE LOGITS
    plets
    0.78
    ulic
    0.77
    teen
    0.76
    plet
    0.71
    ty
    0.71
     digits
    0.66
     triple
    0.65
    ttes
    0.63
    uple
    0.62
     Peaks
    0.62
    Act Density 0.008%

    No Known Activations