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

    Neuronpedia

    INDEX
    Explanations

    mentions of high-ranking positions, such as presidents or executive officers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    nikov
    -0.68
    perate
    -0.65
    TIME
    -0.65
     skirm
    -0.64
    Skill
    -0.61
    condition
    -0.60
    jiang
    -0.60
    EStreamFrame
    -0.59
     snowball
    -0.58
     boulder
    -0.58
    POSITIVE LOGITS
     Shaun
    1.09
     Tony
    1.03
     Jeffrey
    1.01
     Larry
    1.00
     Richard
    0.99
     Geoff
    0.99
     Erik
    0.98
     Darren
    0.97
     Heather
    0.97
     Brendan
    0.97
    Act Density 0.152%

    No Known Activations