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

    Neuronpedia

    INDEX
    Explanations

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

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.63
     beträgt
    -0.54
     electr
    -0.50
    ElementException
    -0.49
    Mediabestanden
    -0.49
    äh
    -0.49
    GroupLayout
    -0.49
     zodat
    -0.48
    adır
    -0.48
    así
    -0.47
    POSITIVE LOGITS
     one
    0.74
    one
    0.73
    One
    0.70
     pasaj
    0.66
    醐
    0.64
    SuppressMessage
    0.62
     resa
    0.61
    arson
    0.61
    Another
    0.61
     Another
    0.61
    Act Density 0.156%

    No Known Activations