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

    Neuronpedia

    INDEX
    Explanations

    mentions of bodies of water, particularly seas

    oai_token-act-pair · gpt-3.5-turbo

    references to seas and bodies of water

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gee
    -0.85
    JECT
    -0.76
     booth
    -0.70
    IO
    -0.69
    Ģ
    -0.68
    IVES
    -0.65
    ioch
    -0.63
    Marginal
    -0.62
    UGC
    -0.61
    udeb
    -0.60
    POSITIVE LOGITS
     Seas
    1.45
     seas
    1.28
     Ocean
    0.97
    boat
    0.94
     oceans
    0.93
    hell
    0.91
     ocean
    0.88
     Sea
    0.86
     shores
    0.85
     waters
    0.83
    Act Density 0.004%

    No Known Activations