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

    Neuronpedia

    INDEX
    Explanations

    words related to mental qualities or sentiments

    oai_token-act-pair · gpt-3.5-turbo

    statements related to confidence and correlation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.82
    dos
    -0.80
    batch
    -0.79
    oultry
    -0.78
    arnaev
    -0.78
    arthed
    -0.74
     asteroids
    -0.73
    storms
    -0.73
     Bombs
    -0.73
     vans
    -0.73
    POSITIVE LOGITS
     loyalty
    1.02
     ability
    1.00
     innate
    0.94
     confidence
    0.92
    Ability
    0.92
     happiness
    0.88
     esteem
    0.86
     humility
    0.85
     feeling
    0.85
     Happiness
    0.84
    Act Density 0.849%

    No Known Activations