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

    Neuronpedia

    INDEX
    Explanations

    website content metadata keywords and tags

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trump
    -0.73
     carn
    -0.68
     lifes
    -0.67
     dece
    -0.66
     princ
    -0.65
     star
    -0.65
     covenant
    -0.65
     behavior
    -0.65
     behaviour
    -0.65
     ticket
    -0.65
    POSITIVE LOGITS
    Advertisements
    1.19
    Related
    1.17
    Similar
    1.06
    Advertisement
    1.05
    Meanwhile
    1.01
    Since
    1.00
    RELATED
    0.98
    ccording
    0.97
    If
    0.96
    JUST
    0.96
    Act Density 0.346%

    No Known Activations