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

    Neuronpedia

    INDEX
    Explanations

    references to specific names or terms

    oai_token-act-pair · gpt-3.5-turbo

    definite articles and related terms frequently used in legal or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leground
    -0.80
    ceans
    -0.79
    Apps
    -0.76
    NBA
    -0.76
    hops
    -0.74
    Ops
    -0.74
    Boost
    -0.73
    AAA
    -0.72
    --+
    -0.71
    Fit
    -0.71
    POSITIVE LOGITS
     earliest
    1.50
     oldest
    1.35
     term
    1.18
    nce
    1.17
     surname
    1.13
     name
    1.12
     inscription
    1.12
     origins
    1.11
     phrase
    1.08
     youngest
    1.06
    Act Density 0.354%

    No Known Activations