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

    Neuronpedia

    INDEX
    Explanations

    durations and time-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     either
    -0.16
     EITHER
    -0.16
     Norris
    -0.16
    plain
    -0.15
    asso
    -0.14
    610
    -0.14
    699
    -0.14
    боÑĢ
    -0.14
    ensi
    -0.14
    91
    -0.13
    POSITIVE LOGITS
     longer
    0.36
     Longer
    0.30
     lifetime
    0.18
    Lifetime
    0.18
    lifetime
    0.18
     shorter
    0.18
    ä¹ĥ
    0.17
     longest
    0.17
     tháºŃm
    0.17
    lif
    0.16
    Act Density 0.085%

    No Known Activations