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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating causality

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causation or reasons for events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivas
    -0.82
     Borderlands
    -0.73
    anooga
    -0.70
    posted
    -0.69
    ©¶æ¥µ
    -0.66
    Reviewed
    -0.64
     Jagu
    -0.64
    iques
    -0.63
    verning
    -0.63
     headlined
    -0.63
    POSITIVE LOGITS
     sheer
    0.85
     exhaustion
    0.82
     lack
    0.76
     injury
    0.75
     clot
    0.73
     ingest
    0.73
     drought
    0.70
     circumstance
    0.68
     accident
    0.68
     neglect
    0.67
    Act Density 0.075%

    No Known Activations