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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "coming" or related phrases indicating upcoming events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovice
    -0.18
    uzey
    -0.15
    ácil
    -0.15
    olson
    -0.15
     defaultProps
    -0.15
    aurant
    -0.15
    ëįĶëĭĪ
    -0.14
    erif
    -0.14
    лоп
    -0.14
    ussen
    -0.14
    POSITIVE LOGITS
     soon
    0.32
    soon
    0.31
     Soon
    0.28
    Soon
    0.26
     attractions
    0.23
     Attr
    0.20
     attraction
    0.20
    les
    0.18
    ling
    0.17
    -of
    0.17
    Act Density 0.020%

    No Known Activations