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

    Neuronpedia

    INDEX
    Explanations

    verbs associated with receiving or approving something

    oai_token-act-pair · gpt-3.5-turbo

    the word "accept" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FTWARE
    -0.68
    ovie
    -0.68
     Anthem
    -0.67
     glands
    -0.65
     afore
    -0.65
     tatt
    -0.63
    folder
    -0.62
    ooming
    -0.61
    APH
    -0.60
    ulz
    -0.59
    POSITIVE LOGITS
    ably
    0.97
     accept
    0.95
    ardless
    0.90
    ibles
    0.87
    Ĥª
    0.85
     accepting
    0.85
     accepts
    0.83
    prises
    0.82
    yip
    0.79
    abilia
    0.79
    Act Density 0.012%

    No Known Activations