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

    Neuronpedia

    INDEX
    Explanations

    mentions of appointing individuals to positions or roles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political appointments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    patch
    -0.88
    olver
    -0.79
    FACE
    -0.78
    1800
    -0.72
    1000
    -0.64
    Heart
    -0.64
     Pound
    -0.64
     nerv
    -0.63
    WARN
    -0.63
     Leth
    -0.63
    POSITIVE LOGITS
     appoint
    1.25
    inates
    1.09
     appointments
    1.04
    ments
    0.99
     appointing
    0.98
     hires
    0.93
    ees
    0.92
     affili
    0.92
    ancies
    0.91
    ially
    0.91
    Act Density 0.005%

    No Known Activations