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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to confidence and self-assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nologue
    -0.60
     Bere
    -0.56
    存于互联网档案馆
    -0.53
    myspace
    -0.53
    aziland
    -0.52
    Denn
    -0.51
     >::
    -0.51
     bearing
    -0.51
    lai
    -0.50
     kal
    -0.50
    POSITIVE LOGITS
    confidence
    1.25
     confidence
    1.21
     confident
    1.19
     Confidence
    1.17
    confident
    1.15
    Confidence
    1.14
     confidently
    0.99
     Shakspeare
    0.89
     houſe
    0.86
     ſta
    0.86
    Act Density 0.046%

    No Known Activations