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

    Neuronpedia

    INDEX
    Explanations

    affirmative statements or expressions of certainty

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

    use of certainly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     head
    -0.40
     bag
    -0.39
     wing
    -0.39
     drop
    -0.37
    ID
    -0.35
     loss
    -0.35
     épis
    -0.35
     dead
    -0.35
     lif
    -0.34
    DOD
    -0.34
    POSITIVE LOGITS
    certainly
    0.95
     certainly
    0.92
    Certainly
    0.82
     Certainly
    0.82
    ptonshire
    0.77
     ciertamente
    0.74
    jména
    0.74
     certamente
    0.73
     sicherlich
    0.69
     deſſen
    0.69
    Act Density 0.006%

    No Known Activations