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

    Neuronpedia

    INDEX
    Explanations

    words related to pigs and pig-related activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and references to pigs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLASSIFIED
    -0.70
    DERR
    -0.69
    ACP
    -0.65
     Wanted
    -0.62
     Christensen
    -0.62
    EMBER
    -0.62
    ãģ®éŃĶ
    -0.61
     Machina
    -0.61
     Profession
    -0.61
     Edison
    -0.60
    POSITIVE LOGITS
    sty
    1.18
    tailed
    1.13
    asus
    1.06
    mentation
    1.03
    gy
    1.00
    tails
    0.98
    lets
    0.92
    mented
    0.90
    meat
    0.87
    tail
    0.86
    Act Density 0.024%

    No Known Activations