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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms containing the word "way"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "way" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asts
    -0.65
     axes
    -0.64
     Gru
    -0.61
    ãģĤ
    -0.60
     exceptions
    -0.58
     basic
    -0.58
    usters
    -0.58
     burg
    -0.57
     concent
    -0.57
     gather
    -0.57
    POSITIVE LOGITS
    way
    1.37
    ways
    1.03
    bill
    1.02
    fare
    1.02
    bos
    0.98
    lane
    0.94
    finding
    0.91
    ward
    0.90
    hole
    0.81
    frame
    0.80
    Act Density 0.007%

    No Known Activations