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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "don" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.84
    ValueStyle
    -0.70
    Msp
    -0.67
     Мексичка
    -0.61
     CURIAM
    -0.59
    Referencie
    -0.59
    BASEPATH
    -0.58
    newArrayList
    -0.58
    WithIOException
    -0.57
    strokeStyle
    -0.55
    POSITIVE LOGITS
     don
    3.00
    don
    2.61
     DON
    2.53
    Don
    2.52
     Don
    2.42
    DON
    2.33
     aren
    1.69
     Dons
    1.68
     doesn
    1.67
     haven
    1.59
    Act Density 0.068%

    No Known Activations