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

    Neuronpedia

    INDEX
    Explanations

    words related to animal welfare or rights

    oai_token-act-pair · gpt-3.5-turbo

    terms related to animal welfare and advocacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heit
    -0.75
    unda
    -0.74
    illing
    -0.72
    ership
    -0.70
     Compton
    -0.70
     Sutherland
    -0.70
    lain
    -0.69
     Wilkinson
    -0.69
    lining
    -0.68
    hips
    -0.68
    POSITIVE LOGITS
     carc
    1.00
     cruelty
    1.00
     kingdom
    0.99
     welfare
    0.93
     welf
    0.92
    arium
    0.90
    istic
    0.89
     animals
    0.87
     shelters
    0.87
     lover
    0.87
    Act Density 0.040%

    No Known Activations