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

    Neuronpedia

    INDEX
    Explanations

    words related to conflict, controversy, and commentary on current events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    FK
    -0.60
     emphasis
    -0.59
     convergence
    -0.59
     Confeder
    -0.58
     genesis
    -0.58
     correlation
    -0.57
     occurrence
    -0.57
    tein
    -0.56
     unlaw
    -0.56
     estimation
    -0.56
    POSITIVE LOGITS
     aback
    1.11
     by
    1.08
    by
    0.88
     BY
    0.84
    wic
    0.79
    uled
    0.79
    pez
    0.79
     merciless
    0.76
    Ń·
    0.75
    quez
    0.71
    Act Density 1.908%

    No Known Activations