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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "sink" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sink" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ordan
    -0.68
    HCR
    -0.62
    OTO
    -0.62
     SX
    -0.61
    APH
    -0.59
    à¦
    -0.58
    leading
    -0.58
     WB
    -0.58
     reckless
    -0.57
     incorrect
    -0.57
    POSITIVE LOGITS
    hole
    1.08
     sink
    1.05
    holes
    1.01
    ucer
    0.98
     sinks
    0.93
    stairs
    0.92
    maid
    0.85
     cellar
    0.83
    vier
    0.82
     ashore
    0.82
    Act Density 0.005%

    No Known Activations