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

    Neuronpedia

    INDEX
    Explanations

    references to pigs and pig-related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to pigs, both literally and metaphorically

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DERR
    -0.77
    EMBER
    -0.71
    ACP
    -0.68
    CLASSIFIED
    -0.67
     Profession
    -0.67
     Unified
    -0.65
     Communication
    -0.65
     Edison
    -0.64
     Christensen
    -0.64
    idential
    -0.63
    POSITIVE LOGITS
    sty
    1.29
    asus
    1.20
    tailed
    1.11
    mentation
    1.05
    tails
    1.02
    gy
    1.01
    meat
    0.97
    mented
    0.93
    warts
    0.93
    artisan
    0.92
    Act Density 0.015%

    No Known Activations