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

    Neuronpedia

    INDEX
    Explanations

    expressions of confidence and assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tages
    -0.62
    ularis
    -0.58
    めでとう
    -0.57
    moveToFirst
    -0.57
    Naissance
    -0.56
     actively
    -0.56
    bingen
    -0.56
    UTIVE
    -0.55
    berge
    -0.55
     extensively
    -0.54
    POSITIVE LOGITS
     certainty
    1.40
     confident
    1.37
     assured
    1.23
     assurance
    1.21
    assured
    1.18
    confident
    1.14
     confidence
    1.14
    certainty
    1.12
    assurance
    1.11
    confidence
    1.07
    Act Density 0.177%

    No Known Activations