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

    Neuronpedia

    INDEX
    Explanations

    past events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to consequences or outcomes of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azel
    -0.71
    ciating
    -0.71
    quire
    -0.70
    etz
    -0.69
    enne
    -0.68
    76561
    -0.68
    amines
    -0.67
    ryu
    -0.66
    atography
    -0.66
    20439
    -0.66
    POSITIVE LOGITS
     tragically
    1.28
     malfunction
    1.20
     vanished
    1.20
     crumbling
    1.16
     mysteriously
    1.16
     collapsed
    1.15
     abruptly
    1.14
     undone
    1.13
     disinteg
    1.12
     collapse
    1.12
    Act Density 0.994%

    No Known Activations