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

    Neuronpedia

    INDEX
    Explanations

    phrases related to capabilities or the lack thereof

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "capability" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    birth
    -0.67
    aternity
    -0.66
    inos
    -0.66
    wind
    -0.66
    eree
    -0.65
    cus
    -0.64
    paying
    -0.64
     Mast
    -0.64
    edi
    -0.63
     Pall
    -0.63
    POSITIVE LOGITS
     capabilities
    1.03
     capability
    0.99
    auga
    0.83
    ibilities
    0.79
    abilities
    0.78
    hered
    0.77
     chops
    0.76
    ilities
    0.75
     capacities
    0.74
    mentation
    0.74
    Act Density 0.019%

    No Known Activations