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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "mark" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tenham
    -0.81
    ····
    -0.77
    katapos
    -0.73
    satunya
    -0.68
    קישורים
    -0.66
    ivotopis
    -0.66
     Montagu
    -0.65
    '/>
    -0.65
    hehehe
    -0.65
    <tbody>
    -0.65
    POSITIVE LOGITS
     Marks
    1.70
     marks
    1.54
    Marks
    1.50
     MARKS
    1.50
     Mark
    1.50
     MARK
    1.50
     mark
    1.45
    Mark
    1.43
    marks
    1.36
    MARK
    1.36
    Act Density 0.099%

    No Known Activations