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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing elements of quantity or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    packed
    -1.87
    amazon
    -1.67
    opia
    -1.63
    strain
    -1.56
    KS
    -1.55
    Street
    -1.54
    tensor
    -1.52
    gas
    -1.49
    tor
    -1.46
    Fried
    -1.45
    POSITIVE LOGITS
    ¦
    2.23
    į
    1.86
    ¯
    1.85
    µ
    1.81
    Ĺ
    1.80
    º
    1.72
    °
    1.66
    ·
    1.65
    ĨĴ
    1.64
     unless
    1.61
    Act Density 0.131%

    No Known Activations