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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to interactions and interfaces in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hochspringen
    -0.64
     estimés
    -0.57
    ///</
    -0.50
    下载附件
    -0.50
     Masked
    -0.49
    fördert
    -0.49
    BRC
    -0.47
    ifrance
    -0.47
    elemField
    -0.47
    NSON
    -0.46
    POSITIVE LOGITS
     Inters
    0.85
    inter
    0.80
    Inter
    0.80
     inter
    0.79
    INTER
    0.77
     تضيفلها
    0.75
     inters
    0.73
     Inter
    0.68
     INTER
    0.67
     interstate
    0.66
    Act Density 2.639%

    No Known Activations