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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    the word "Occasionally" and other words related to infrequency or rarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ballard
    -0.91
    hawk
    -0.88
     Birch
    -0.86
     Hamm
    -0.84
     Redmond
    -0.84
    Plex
    -0.82
     Bash
    -0.76
     Crow
    -0.73
     Fowler
    -0.73
     Airways
    -0.72
    POSITIVE LOGITS
    milo
    0.70
     phyl
    0.70
     reorgan
    0.70
     grade
    0.66
     (=
    0.65
    代
    0.65
     reconc
    0.64
     folders
    0.63
     photoc
    0.63
     includ
    0.63
    Act Density 0.000%

    No Known Activations