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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the creation or modification of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.55
    NameInMap
    -0.52
    VideoCapture
    -0.50
    makeConstraints
    -0.47
    +//
    -0.46
    COUVER
    -0.43
    <eos>
    -0.43
    πως
    -0.42
    ogaster
    -0.41
     fra
    -0.41
    POSITIVE LOGITS
     themſelves
    0.73
     Efq
    0.71
     $_"
    0.70
    ſelf
    0.69
     manhood
    0.69
    imah
    0.69
    ^(@)
    0.69
     myſelf
    0.68
     Theſe
    0.67
     comprehensive
    0.66
    Act Density 0.325%

    No Known Activations