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

    Neuronpedia

    INDEX
    Explanations

    references to vice presidential positions and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    splan
    -0.73
    }?>
    -0.70
    σμα
    -0.69
     samar
    -0.69
     Hurricanes
    -0.68
    ]();
    -0.67
    rishnan
    -0.67
     Teres
    -0.66
    temun
    -0.66
     colonists
    -0.66
    POSITIVE LOGITS
     Vice
    1.34
     VICE
    1.30
     vice
    1.26
    Vice
    1.22
     versa
    1.05
    vice
    1.03
     vise
    0.82
     Vise
    0.80
    versa
    0.79
     vices
    0.79
    Act Density 0.061%

    No Known Activations