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

    Neuronpedia

    INDEX
    Explanations

    expressions of confidence and self-esteem

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ber
    -0.70
    gdx
    -0.69
    asley
    -0.66
    к
    -0.64
     Brink
    -0.62
    sel
    -0.62
    ollectionView
    -0.61
     ber
    -0.60
     tark
    -0.60
    чан
    -0.60
    POSITIVE LOGITS
     confidence
    1.74
    confidence
    1.65
     Confidence
    1.60
     confident
    1.53
    Confidence
    1.46
    confident
    1.43
     confidently
    1.31
     itſelf
    1.29
     myſelf
    1.25
     confiance
    1.19
    Act Density 0.061%

    No Known Activations