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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "bay"

    oai_token-act-pair · gpt-3.5-turbo

    references to "bay"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ru
    -0.76
     Inher
    -0.73
    ilateral
    -0.73
    rupted
    -0.72
     Parents
    -0.72
     Parent
    -0.72
    Parent
    -0.70
    odies
    -0.67
    Parents
    -0.67
     Rept
    -0.65
    POSITIVE LOGITS
     bay
    4.34
    bay
    2.22
     Bay
    2.11
    Bay
    1.92
     docks
    1.20
     harbour
    1.10
     dock
    1.03
     sab
    0.99
     harbor
    0.96
     wal
    0.89
    Act Density 0.011%

    No Known Activations