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

    Neuronpedia

    INDEX
    Explanations

    statements reflecting beliefs or thoughts about various subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating belief or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ECK
    -0.66
     Submission
    -0.65
    Newsletter
    -0.62
    ample
    -0.60
     VIDEOS
    -0.58
    Exit
    -0.56
    ISE
    -0.55
     Invention
    -0.55
    Feature
    -0.54
    cession
    -0.54
    POSITIVE LOGITS
     to
    1.14
    to
    0.77
     responsible
    0.76
     destined
    0.76
     by
    0.70
     capable
    0.70
    fully
    0.67
     guilty
    0.67
    ocry
    0.67
     thereto
    0.64
    Act Density 0.073%

    No Known Activations