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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation and transformation over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UpdatedAt
    -0.17
    _pb
    -0.15
    emean
    -0.15
     може
    -0.14
     Recently
    -0.14
    asher
    -0.14
    ÂĪ
    -0.14
     lately
    -0.14
    504
    -0.13
     Recent
    -0.13
    POSITIVE LOGITS
     later
    0.52
     eventual
    0.50
     eventually
    0.48
    later
    0.42
     Eventually
    0.41
     would
    0.39
     soon
    0.39
    Eventually
    0.37
     Later
    0.36
    Later
    0.36
    Act Density 0.146%

    No Known Activations