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

    Neuronpedia

    INDEX
    Explanations

    words related to support or impact

    oai_token-act-pair · gpt-3.5-turbo

    the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icons
    -0.81
    aws
    -0.78
    vich
    -0.77
    acers
    -0.75
    cks
    -0.73
    witz
    -0.73
    masters
    -0.72
    isms
    -0.71
    ashes
    -0.70
    lee
    -0.68
    POSITIVE LOGITS
     particular
    1.10
     newfound
    0.93
     country
    0.90
     week
    0.89
     century
    0.89
     trope
    0.88
     topic
    0.88
     endeavor
    0.87
     hemisphere
    0.86
     illustrious
    0.86
    Act Density 0.224%

    No Known Activations