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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating untapped or future capabilities

    oai_token-act-pair · gpt-3.5-turbo

    statements about potential or opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.84
    ograph
    -0.77
    chet
    -0.73
    ching
    -0.73
    cise
    -0.71
    cott
    -0.68
    cloth
    -0.68
    men
    -0.67
    ogie
    -0.65
    OTO
    -0.65
    POSITIVE LOGITS
    izons
    0.98
    ities
    0.91
    ibilities
    0.89
     implications
    0.83
    atility
    0.81
     usefulness
    0.81
     payoff
    0.80
     futures
    0.77
    urities
    0.77
    00007
    0.76
    Act Density 0.024%

    No Known Activations