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

    Neuronpedia

    INDEX
    Explanations

    names and partial names of individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.66
     seeker
    -0.65
    ĪĴ
    -0.64
    iltration
    -0.63
    minist
    -0.62
    ModLoader
    -0.61
    rar
    -0.61
    ught
    -0.60
    cair
    -0.59
     fug
    -0.59
    POSITIVE LOGITS
    zyk
    0.98
    owicz
    0.80
    osaurus
    0.75
    opol
    0.66
     Sabha
    0.65
     Phill
    0.65
    ée
    0.64
     Krish
    0.63
     Weeks
    0.63
    quez
    0.63
    Act Density 0.209%

    No Known Activations