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

    Neuronpedia

    INDEX
    Explanations

    the word "Sea"

    oai_token-act-pair · gpt-3.5-turbo

    references to various seas or bodies of water

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pun
    -0.86
    interstitial
    -0.77
    UID
    -0.71
    ibl
    -0.68
    abol
    -0.66
    bul
    -0.63
    COMPLE
    -0.63
    bh
    -0.63
     muff
    -0.63
     remed
    -0.62
    POSITIVE LOGITS
     Sea
    4.05
    Sea
    3.10
     Seas
    2.30
     sea
    2.23
    sea
    1.81
     SEA
    1.74
     seas
    1.73
     Ocean
    1.53
    Ocean
    1.44
     Seaf
    1.42
    Act Density 0.014%

    No Known Activations