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

    Neuronpedia

    INDEX
    Explanations

    references to specific types of seals, particularly the "elephant seal."

    oai_token-act-pair · gpt-3.5-turbo

    references to different species of seals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itters
    -0.73
    enegger
    -0.69
    chy
    -0.67
    orne
    -0.67
     Ort
    -0.66
    schild
    -0.66
     Drawn
    -0.66
     Rove
    -0.63
    cart
    -0.62
     Lov
    -0.62
    POSITIVE LOGITS
     seal
    1.35
     seals
    1.24
     sealing
    0.96
     Seal
    0.89
    ife
    0.87
    keeper
    0.79
    heed
    0.78
    wrap
    0.75
    ldom
    0.75
     oath
    0.72
    Act Density 0.007%

    No Known Activations