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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "Department" with varying importance levels

    oai_token-act-pair · gpt-3.5-turbo

    references to deportation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pose
    -0.83
    nings
    -0.82
    ç¥ŀ
    -0.79
    ãĥīãĥ©ãĤ´ãĥ³
    -0.75
    Reviewer
    -0.74
    éŃĶ
    -0.74
     Kens
    -0.69
    ä¸ī
    -0.69
    SPONSORED
    -0.66
    ties
    -0.65
    POSITIVE LOGITS
    recated
    1.10
    artments
    1.01
    dep
    1.00
     Dep
    0.99
    uty
    0.98
    rived
    0.97
    Dep
    0.92
    enture
    0.92
    utation
    0.92
    encies
    0.91
    Act Density 0.004%

    No Known Activations