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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions and interactions between people

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.74
    selves
    -0.69
    wcsstore
    -0.67
    Supplement
    -0.64
     selves
    -0.63
    definition
    -0.61
     ILCS
    -0.61
    Attach
    -0.58
    Therefore
    -0.58
    aspx
    -0.58
    POSITIVE LOGITS
     himself
    1.12
     Himself
    0.86
     herself
    0.85
     his
    0.84
     tirelessly
    0.68
     brilliantly
    0.67
     us
    0.66
     yesterday
    0.66
     me
    0.64
     LAST
    0.64
    Act Density 0.526%

    No Known Activations