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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    articles and descriptive phrases that indicate specific characteristics or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     annually
    -0.77
    Contents
    -0.70
    imester
    -0.69
     Income
    -0.64
     Assets
    -0.64
    iments
    -0.63
    Sources
    -0.63
     herein
    -0.63
    SI
    -0.62
    Own
    -0.62
    POSITIVE LOGITS
     handful
    1.05
     few
    1.04
     flurry
    1.01
     frantic
    1.01
     sudden
    1.00
     grin
    0.96
     flashback
    0.95
     couple
    0.95
     furious
    0.95
     heartbeat
    0.94
    Act Density 0.331%

    No Known Activations