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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to family relationships and newborns

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Rounds
    -0.69
     Kitty
    -0.66
    SIGN
    -0.65
     Salon
    -0.65
    PN
    -0.65
    GMT
    -0.65
     Pharaoh
    -0.64
     Ov
    -0.64
     Rothschild
    -0.62
     Mobil
    -0.62
    POSITIVE LOGITS
    selves
    1.32
    lightly
    1.13
    pecially
    1.09
    atisf
    1.09
    aying
    1.07
    ELF
    1.04
    ources
    1.04
    ustainable
    1.03
    omew
    1.03
    uddenly
    1.03
    Act Density 9.212%

    No Known Activations