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

    Neuronpedia

    INDEX
    Explanations

    information related to numbers and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to casualties or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Conserv
    -0.56
     Limbaugh
    -0.54
     Feel
    -0.52
    RAW
    -0.52
    Management
    -0.51
     Expect
    -0.50
    entimes
    -0.50
    Hide
    -0.49
     Tune
    -0.48
    nature
    -0.48
    POSITIVE LOGITS
     apiece
    0.74
    undred
    0.67
    illion
    0.65
    imore
    0.64
    iversary
    0.61
     increments
    0.60
    pees
    0.59
     acres
    0.57
    milo
    0.56
    ottest
    0.55
    Act Density 1.791%

    No Known Activations