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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social issues and societal challenges, such as poverty, tipping models, political conflicts, and public policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Comet
    -0.57
    REDACTED
    -0.56
     Tarant
    -0.56
     Its
    -0.56
     Seller
    -0.55
     nutshell
    -0.55
     reviewer
    -0.54
    Guy
    -0.53
     (@
    -0.52
    Reader
    -0.51
    POSITIVE LOGITS
     themselves
    1.51
     their
    1.09
    selves
    1.07
     careers
    1.05
     selves
    1.03
    their
    1.00
     THEIR
    0.92
     voluntarily
    0.88
    utterstock
    0.85
     willingly
    0.82
    Act Density 0.862%

    No Known Activations