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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences describing the potential for something to happen or achieve a specific outcome

    oai_token-act-pair · gpt-3.5-turbo

    references to potential in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.75
    ching
    -0.75
    cloth
    -0.71
    ograph
    -0.70
    chet
    -0.69
    cise
    -0.68
    bows
    -0.68
    men
    -0.66
    gaard
    -0.66
    onest
    -0.66
    POSITIVE LOGITS
    izons
    0.96
    ities
    0.94
     usefulness
    0.88
    ibilities
    0.86
    atility
    0.84
     implications
    0.81
     payoff
    0.77
     synerg
    0.75
    ity
    0.72
     futures
    0.72
    Act Density 0.026%

    No Known Activations