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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to capabilities and abilities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    birth
    -0.77
    orno
    -0.77
    idan
    -0.71
    eree
    -0.71
    corn
    -0.69
    hus
    -0.66
    inos
    -0.65
    esta
    -0.64
    eros
    -0.64
    cott
    -0.64
    POSITIVE LOGITS
     capabilities
    1.06
     capability
    0.96
    abilities
    0.88
    hered
    0.87
    BILITIES
    0.84
     conferred
    0.84
     limitations
    0.82
     capacities
    0.79
     limitation
    0.79
     upgrades
    0.78
    Act Density 0.033%

    No Known Activations