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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey certainty and assurance

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

    assurance or certainty

    np_acts-logits-general · gemini-2.0-flash

    guaranteed to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    halb
    -0.54
    Vielleicht
    -0.53
     perhaps
    -0.53
    BEGIN
    -0.53
    nun
    -0.53
     Holl
    -0.52
    substack
    -0.52
     nicely
    -0.51
    middot
    -0.50
     nat
    -0.49
    POSITIVE LOGITS
     guaranteed
    1.18
     guarantee
    1.10
     assured
    0.97
     guarantees
    0.97
     certainty
    0.95
     Guaranteed
    0.94
    guarantee
    0.93
     Guarantee
    0.92
    anteed
    0.91
    Guaranteed
    0.90
    Act Density 0.216%

    No Known Activations