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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating position or roles within an organization or community context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    167
    -0.16
    olik
    -0.15
    fi
    -0.15
    illon
    -0.14
     loos
    -0.14
    lin
    -0.14
    mini
    -0.13
    emed
    -0.13
    267
    -0.13
    rl
    -0.13
    POSITIVE LOGITS
    irst
    0.16
    DonaldTrump
    0.15
    tain
    0.15
    assi
    0.15
    iciary
    0.14
    eson
    0.14
    èĤĸ
    0.14
    IRST
    0.14
     TOR
    0.14
    оÑĢони
    0.14
    Act Density 0.308%

    No Known Activations