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

    Neuronpedia

    INDEX
    Explanations

    references to online profiles, user attributes, and personal information on the internet

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    actic
    -0.81
    nuts
    -0.80
    shall
    -0.71
    hers
    -0.71
     relent
    -0.70
    agan
    -0.68
    mental
    -0.68
    abeth
    -0.67
    iculture
    -0.67
    meat
    -0.66
    POSITIVE LOGITS
     profile
    1.07
     profiles
    1.06
    ocl
    0.88
    onym
    0.84
    Profile
    0.80
     picture
    0.79
     Seym
    0.75
    schild
    0.71
     Picture
    0.71
    ographies
    0.70
    Act Density 11.178%

    No Known Activations