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

    Neuronpedia

    INDEX
    Explanations

    words related to additional actions or items

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "also."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agus
    -0.61
    acious
    -0.60
    jam
    -0.60
    ash
    -0.59
    inho
    -0.57
    idden
    -0.55
     Creation
    -0.55
     Yin
    -0.54
     Chaser
    -0.54
    Earth
    -0.54
    POSITIVE LOGITS
     includ
    0.77
     includes
    0.72
     noteworthy
    0.70
     included
    0.67
     cautioned
    0.65
     notable
    0.65
     anecd
    0.64
     confir
    0.64
     optionally
    0.62
     moder
    0.62
    Act Density 0.058%

    No Known Activations