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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an additional point or detail in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "also."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orum
    -0.70
    cies
    -0.70
    ouses
    -0.66
    ocene
    -0.63
    apons
    -0.60
    regate
    -0.60
    anwhile
    -0.60
    urches
    -0.60
    glers
    -0.58
     VIDEOS
    -0.57
    POSITIVE LOGITS
     noteworthy
    0.86
     referred
    0.80
     notable
    0.78
     known
    0.76
     implicated
    0.76
     reportedly
    0.75
     applicable
    0.75
     responsible
    0.74
     borne
    0.70
     reflected
    0.70
    Act Density 0.108%

    No Known Activations