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

    Neuronpedia

    INDEX
    Explanations

    mentions of technological capabilities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various capabilities and skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eree
    -0.72
    birth
    -0.71
    paying
    -0.67
    corn
    -0.67
    tale
    -0.66
    boys
    -0.66
    orno
    -0.65
    cus
    -0.64
    ÃŃa
    -0.64
    cott
    -0.64
    POSITIVE LOGITS
     capabilities
    1.01
     capability
    0.94
    abilities
    0.81
    hered
    0.76
    Ability
    0.73
    mentation
    0.73
     capacities
    0.73
     gaps
    0.72
     conferred
    0.72
     abilities
    0.71
    Act Density 0.033%

    No Known Activations