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

    Neuronpedia

    INDEX
    Explanations

    mentions of oceanic locations

    oai_token-act-pair · gpt-3.5-turbo

    references to various oceans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TI
    -0.81
    TOP
    -0.75
    oulder
    -0.74
    enez
    -0.73
    Reloaded
    -0.72
    ENCE
    -0.72
    enance
    -0.69
    UGC
    -0.68
    éĹ
    -0.67
    Interstitial
    -0.67
    POSITIVE LOGITS
     Ocean
    1.15
    ographer
    1.07
    front
    0.95
     Atlantic
    0.91
    ographers
    0.89
    odon
    0.89
     Fisheries
    0.88
    ographic
    0.88
     basin
    0.84
     Spray
    0.83
    Act Density 0.014%

    No Known Activations