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

    Neuronpedia

    INDEX
    Explanations

    phrases related to possession or control by an individual or group

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    bda
    -0.89
    ffer
    -0.81
    ept
    -0.79
    Champ
    -0.71
    andering
    -0.69
     Cosponsors
    -0.68
    thinking
    -0.68
    still
    -0.67
    stellar
    -0.67
    hazard
    -0.67
    POSITIVE LOGITS
     rewritten
    0.80
     doors
    0.74
     legislation
    0.73
     dismantled
    0.71
     overturned
    0.71
     reopened
    0.70
     removal
    0.70
     turbines
    0.69
     reinstated
    0.69
     reversed
    0.69
    Act Density 0.321%

    No Known Activations