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

    Neuronpedia

    INDEX
    Explanations

    words related to confidence, achievement, and personal traits

    oai_token-act-pair · gpt-3.5-turbo

    expressions of certainty and uncertainty in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earch
    -0.61
     unison
    -0.59
    aum
    -0.56
    merce
    -0.56
    inav
    -0.54
    anooga
    -0.53
    swick
    -0.52
    were
    -0.52
    iscons
    -0.51
    oslov
    -0.51
    POSITIVE LOGITS
     himself
    1.10
     Himself
    0.81
     herself
    0.79
     his
    0.78
     cameo
    0.68
     solo
    0.64
     autobiography
    0.63
    itone
    0.61
     HIS
    0.61
     charisma
    0.60
    Act Density 1.494%

    No Known Activations