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

    Neuronpedia

    INDEX
    Explanations

    expressions of confidence and certainty

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

    "confidence" or demonstrating ability

    np_acts-logits-general · gemini-2.0-flash

    confidence, self, demonstrated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ness
    -0.73
    west
    -0.70
    rd
    -0.69
    w
    -0.69
    ings
    -0.68
    mou
    -0.67
    ι
    -0.67
    mos
    -0.67
    r
    -0.66
    k
    -0.64
    POSITIVE LOGITS
     itſelf
    1.29
     themſelves
    1.25
     myſelf
    1.20
     Monfieur
    1.20
     againſt
    1.11
     purpoſe
    1.06
     becauſe
    1.06
    ſelf
    1.05
     ſeveral
    1.04
     himſelf
    1.04
    Act Density 0.216%

    No Known Activations