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

    Neuronpedia

    INDEX
    Explanations

    references to pools and water-related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.68
    ⓧ
    -0.63
    textwidth
    -0.62
     betweenstory
    -0.57
    zarchiwizowane
    -0.57
    DoubleQuotes
    -0.57
    дента
    -0.57
    makeConstraints
    -0.56
    دانشنامهٔ
    -0.53
     мәкал
    -0.52
    POSITIVE LOGITS
     pool
    1.03
     Pool
    0.94
    Pool
    0.84
     POOL
    0.84
     liner
    0.82
    pool
    0.81
     pump
    0.77
     chlorine
    0.77
    POOL
    0.73
     Pools
    0.73
    Act Density 0.166%

    No Known Activations