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

    Neuronpedia

    INDEX
    Explanations

    references to organizational roles and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     staff
    -0.16
    staff
    -0.15
     Staff
    -0.14
     geile
    -0.14
    gue
    -0.14
    Staff
    -0.14
     supervisor
    -0.14
    çŀ
    -0.14
     supervision
    -0.14
    orget
    -0.14
    POSITIVE LOGITS
     vice
    0.29
     Vice
    0.27
    asurer
    0.27
     president
    0.25
     officers
    0.25
    vice
    0.24
     secretary
    0.24
     President
    0.24
     chair
    0.23
     presidents
    0.23
    Act Density 0.144%

    No Known Activations