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

    Neuronpedia

    INDEX
    Explanations

    animal-related terms, specifically related to pigs

    oai_token-act-pair · gpt-3.5-turbo

    references to pigs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Machina
    -0.72
     Wel
    -0.68
     Profession
    -0.63
     Edison
    -0.59
     disruption
    -0.57
     Communication
    -0.56
    DERR
    -0.55
    Oracle
    -0.55
     ÙĪ
    -0.55
    ECA
    -0.55
    POSITIVE LOGITS
    gy
    1.43
    mentation
    1.34
    sty
    1.33
    tails
    1.30
    tailed
    1.29
    mented
    1.24
    gery
    1.19
    tail
    1.18
    ged
    1.17
    ging
    1.15
    Act Density 0.058%

    No Known Activations