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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to royalty and history

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     forth
    -0.76
     DRAG
    -0.75
    bell
    -0.70
    âĵĺ
    -0.66
     weighted
    -0.66
     Belt
    -0.64
     weighing
    -0.63
     Universal
    -0.63
     multiplied
    -0.62
     Nielsen
    -0.61
    POSITIVE LOGITS
    acy
    1.20
    atche
    1.07
    ips
    1.05
    acists
    1.04
    acies
    1.03
    ife
    1.02
    cipled
    1.01
    iple
    1.00
    £
    0.99
    aughter
    0.99
    Act Density 0.044%

    No Known Activations