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

    Neuronpedia

    INDEX
    Explanations

    words related to self-improvement and self-empowerment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to self-help and self-improvement concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estone
    -0.85
    sea
    -0.84
    ugu
    -0.82
    endez
    -0.82
    meric
    -0.79
    staff
    -0.74
    estones
    -0.73
    usky
    -0.70
    eston
    -0.67
    weather
    -0.66
    POSITIVE LOGITS
     prophecy
    0.78
     narciss
    0.68
     ide
    0.65
     goodness
    0.65
     spirituality
    0.64
     guru
    0.64
     behaviors
    0.64
     oats
    0.62
    utterstock
    0.62
     checklist
    0.61
    Act Density 0.088%

    No Known Activations