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

    Neuronpedia

    INDEX
    Explanations

    words related to actions and events that involve physical movement or interaction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve actions or conditions followed by the conjunction "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Contents
    -0.83
    utenberg
    -0.81
    dayName
    -0.81
    CLASSIFIED
    -0.71
    Disk
    -0.68
    ajor
    -0.65
    ANC
    -0.65
     Older
    -0.63
     Corpus
    -0.62
    confirmed
    -0.62
    POSITIVE LOGITS
     THEN
    1.28
     then
    1.23
     suddenly
    1.12
     magically
    0.96
     reap
    0.90
     pretend
    0.89
     thereby
    0.89
     somehow
    0.88
     forget
    0.85
     prest
    0.83
    Act Density 0.308%

    No Known Activations