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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey reassurance and confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Persona
    -0.16
    cheng
    -0.15
    azzi
    -0.15
    umper
    -0.14
    jÃŃ
    -0.14
    fleet
    -0.14
    ãĥĥãĤ°
    -0.14
     ÐĵÑĢи
    -0.14
    oons
    -0.13
    enton
    -0.13
    POSITIVE LOGITS
     confidence
    0.36
     confident
    0.31
     Confidence
    0.30
     assurance
    0.28
    confidence
    0.27
     rest
    0.24
     worry
    0.23
     assured
    0.23
     confidently
    0.22
     certainty
    0.22
    Act Density 0.136%

    No Known Activations