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

    Neuronpedia

    INDEX
    Explanations

    references to crashes and failures, particularly in the context of technology and vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UNE
    -0.17
    cken
    -0.17
    iferay
    -0.16
    anc
    -0.16
    ally
    -0.15
    tle
    -0.15
    zial
    -0.15
    herits
    -0.15
    gle
    -0.15
    gres
    -0.14
    POSITIVE LOGITS
    (es
    0.21
     Crash
    0.20
     landing
    0.18
    ingly
    0.18
    bum
    0.18
    y
    0.18
     crash
    0.17
    eroon
    0.17
    landing
    0.17
     Landing
    0.16
    Act Density 0.018%

    No Known Activations