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

    Neuronpedia

    INDEX
    Explanations

    references to official delegations and visits

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ammon
    -0.73
    =#
    -0.73
    corn
    -0.72
     ammonia
    -0.72
    utenberg
    -0.71
    pmwiki
    -0.68
    ãĥĸ
    -0.67
    erenn
    -0.65
    stocks
    -0.65
    OIL
    -0.64
    POSITIVE LOGITS
     deleg
    1.11
     delegation
    0.95
     helicop
    0.85
     assembled
    0.83
    ongyang
    0.82
     toured
    0.81
    ees
    0.80
    naires
    0.79
     tasked
    0.78
     dispatched
    0.77
    Act Density 0.022%

    No Known Activations