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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical sinks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sink" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTO
    -0.64
    ordan
    -0.63
    APH
    -0.62
    à¦
    -0.61
    Whe
    -0.61
    PRES
    -0.60
     Austral
    -0.60
     challenging
    -0.59
     Huffington
    -0.59
     portraying
    -0.59
    POSITIVE LOGITS
     sink
    1.27
     sinks
    1.20
    ucer
    1.05
    hole
    0.96
     sinking
    0.90
    boat
    0.82
     ashore
    0.81
    vier
    0.80
    holes
    0.79
    pipe
    0.79
    Act Density 0.005%

    No Known Activations