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

    Neuronpedia

    INDEX
    Explanations

    prominent personalities and figures, such as entrepreneurs, actors, and political commentators

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Ire
    -0.71
    isks
    -0.70
     Agric
    -0.68
    Els
    -0.68
     Sakura
    -0.67
     Wasserman
    -0.65
    cul
    -0.63
    oard
    -0.63
     Krish
    -0.62
     Ginny
    -0.61
    POSITIVE LOGITS
     Jr
    1.06
     famously
    0.85
     III
    0.84
     QC
    0.83
     Sr
    0.83
    agher
    0.82
     aka
    0.78
    enburg
    0.71
     ushered
    0.67
     fame
    0.66
    Act Density 0.198%

    No Known Activations