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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sequence of events or actions, particularly those that begin with "After."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after an event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.70
    expandindo
    -0.60
    +:+
    -0.59
     utafitiHapana
    -0.59
    PyExc
    -0.53
    ertos
    -0.52
    esgue
    -0.52
    #
    -0.52
    findpost
    -0.52
    antic
    -0.52
    POSITIVE LOGITS
     After
    0.54
    After
    0.47
     Once
    0.45
    Setelah
    0.44
    katapos
    0.42
    Once
    0.41
     Setelah
    0.41
     Upon
    0.37
     after
    0.36
    IVEREF
    0.36
    Act Density 0.040%

    No Known Activations