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

    Neuronpedia

    INDEX
    Explanations

    temporal expressions or phrases indicating sequences of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anytime
    -0.15
     anywhere
    -0.14
     whenever
    -0.14
    doing
    -0.13
    building
    -0.13
     ourselves
    -0.13
     Adds
    -0.13
     Himself
    -0.13
    ully
    -0.12
     vá»įng
    -0.12
    POSITIVE LOGITS
     being
    0.26
     they
    0.25
     it
    0.24
     revelations
    0.21
     learning
    0.20
     suffering
    0.20
     narrowly
    0.19
     he
    0.19
     news
    0.19
     abruptly
    0.18
    Act Density 0.093%

    No Known Activations