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

    Neuronpedia

    INDEX
    Explanations

    positive attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe individuals with specific attributes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reinforcements
    -0.76
    agents
    -0.72
     exercises
    -0.71
     adventurers
    -0.69
    aways
    -0.69
     operators
    -0.69
     volunteers
    -0.68
     councils
    -0.66
    Contents
    -0.66
     scenes
    -0.65
    POSITIVE LOGITS
     penchant
    1.13
     knack
    1.04
     vested
    1.03
     propensity
    0.97
     uterus
    0.88
     clipboard
    0.88
     passion
    0.86
     disability
    0.84
     tendency
    0.83
     predis
    0.81
    Act Density 0.157%

    No Known Activations