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

    Neuronpedia

    INDEX
    Explanations

    references to sightings or observations of people

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "seen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angan
    -0.73
    mental
    -0.71
    idity
    -0.70
    sett
    -0.68
    otomy
    -0.64
     assignment
    -0.63
    cussion
    -0.62
     anthem
    -0.61
     spinal
    -0.60
    aceutical
    -0.60
    POSITIVE LOGITS
    IOR
    0.86
    ById
    0.85
    wcsstore
    0.82
    IRT
    0.81
    swick
    0.80
    hao
    0.77
    dust
    0.75
    seeing
    0.72
    Ĺ
    0.71
    PsyNetMessage
    0.71
    Act Density 0.036%

    No Known Activations