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

    Neuronpedia

    INDEX
    Explanations

    references to time durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aproxim
    -0.16
    боÑĢ
    -0.15
    700
    -0.15
    esper
    -0.14
    900
    -0.14
    illion
    -0.14
    400
    -0.14
    kok
    -0.14
    asso
    -0.14
    .avg
    -0.13
    POSITIVE LOGITS
     longer
    0.34
     Longer
    0.28
    asics
    0.18
     months
    0.17
     years
    0.17
    ?url
    0.17
     decades
    0.16
     longest
    0.16
    Lifetime
    0.16
     shorter
    0.16
    Act Density 0.034%

    No Known Activations