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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "confidence" with varying levels of intensity

    oai_token-act-pair · gpt-3.5-turbo

    expressions and references related to confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aters
    -0.80
    arium
    -0.75
    ater
    -0.69
     Eater
    -0.69
     Sod
    -0.67
    rant
    -0.67
    ogs
    -0.66
    arry
    -0.66
    ario
    -0.62
    listed
    -0.62
    POSITIVE LOGITS
     confidence
    3.90
    confidence
    2.76
     trust
    1.89
     confident
    1.74
     credibility
    1.67
     assurance
    1.66
     certainty
    1.62
     optimism
    1.61
     faith
    1.55
     esteem
    1.35
    Act Density 0.008%

    No Known Activations