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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "After"

    oai_token-act-pair · gpt-3.5-turbo

    the word "After" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OO
    -0.69
    amount
    -0.66
    oys
    -0.66
    NRS
    -0.66
    uci
    -0.61
    åŃ
    -0.61
    uns
    -0.61
    ãĤ¹ãĥĪ
    -0.61
    atics
    -0.61
    ����
    -0.61
    POSITIVE LOGITS
    noon
    1.17
    wards
    1.06
    ward
    1.02
    word
    0.99
    math
    0.93
    words
    0.85
    market
    0.79
    forming
    0.78
     graduating
    0.77
    Ļ½
    0.75
    Act Density 0.077%

    No Known Activations