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

    Neuronpedia

    INDEX
    Explanations

    references to various deputy positions across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roje
    -0.17
     Honey
    -0.15
     hra
    -0.15
    otta
    -0.15
    pell
    -0.15
    pNet
    -0.15
    åºŃ
    -0.14
    rahim
    -0.14
    zug
    -0.14
    anja
    -0.14
    POSITIVE LOGITS
     mayor
    0.20
    ship
    0.18
     sheriff
    0.18
     Mayor
    0.17
     editor
    0.16
    dom
    0.16
     gross
    0.15
    -major
    0.15
     marshal
    0.15
    -editor
    0.15
    Act Density 0.009%

    No Known Activations