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

    Neuronpedia

    INDEX
    Explanations

    phrases related to professional career changes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    uca
    -0.70
     neigh
    -0.67
    uph
    -0.66
    anus
    -0.64
    udes
    -0.62
    tons
    -0.61
     answer
    -0.61
     naughty
    -0.61
     assurance
    -0.61
     moan
    -0.61
    POSITIVE LOGITS
    Appearances
    1.21
    References
    1.16
    However
    1.10
    History
    1.10
    Notable
    1.09
    Trivia
    1.09
    Appearance
    1.07
    Meanwhile
    1.06
    Gameplay
    1.06
    Nevertheless
    1.05
    Act Density 12.258%

    No Known Activations