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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating periods of time or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Weeks
    -0.17
     hôm
    -0.15
    weeks
    -0.14
    bÃŃr
    -0.14
     Hava
    -0.14
    387
    -0.13
    Days
    -0.13
    72
    -0.13
    éments
    -0.13
    actus
    -0.13
    POSITIVE LOGITS
     decade
    0.60
    dec
    0.57
     Dec
    0.50
     dec
    0.46
     decades
    0.45
    Dec
    0.43
     déc
    0.42
    _dec
    0.42
    -de
    0.40
    .dec
    0.40
    Act Density 0.076%

    No Known Activations