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

    Neuronpedia

    INDEX
    Explanations

    the word "obviously" and its variations, indicating a focus on statements that express certainty or clear understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    obviously or of course

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.63
     lenker
    -0.54
     <=",
    -0.50
     Winaray
    -0.49
    Географиясе
    -0.48
     שוליים
    -0.48
     betweenstory
    -0.48
    .*")]
    -0.47
     <<<<<<<<<<<<<<
    -0.46
    Autoritní
    -0.46
    POSITIVE LOGITS
    obviously
    0.92
     obviously
    0.91
    Obviously
    0.88
     Obviously
    0.86
    eraard
    0.80
     obviamente
    0.77
     ovviamente
    0.73
     évidemment
    0.71
     natürlich
    0.70
    Natürlich
    0.68
    Act Density 0.045%

    No Known Activations