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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    specific names and identities of individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.59
     compr
    -0.56
    nown
    -0.53
    uminati
    -0.53
    âķIJâķIJ
    -0.52
     ..........
    -0.52
    alpha
    -0.52
    ãĢIJ
    -0.51
    oooooooo
    -0.50
     mathemat
    -0.47
    POSITIVE LOGITS
     KE
    0.58
    ECK
    0.54
     detractors
    0.54
    ees
    0.50
     quotes
    0.49
     EG
    0.49
     Jinn
    0.48
     concludes
    0.47
     Gad
    0.47
     Voting
    0.47
    Act Density 0.791%

    No Known Activations