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

    Neuronpedia

    INDEX
    Explanations

    references to specific government administrations, particularly related to the Trump administration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ks
    -0.16
    ãĥ¬ãĥĥãĥĪ
    -0.15
    iem
    -0.15
    æľ¬
    -0.14
    orget
    -0.14
    ILLS
    -0.14
    Ñĥков
    -0.14
    wend
    -0.14
     Gast
    -0.14
    essional
    -0.13
    POSITIVE LOGITS
    thood
    0.15
     èĬ±
    0.14
    alley
    0.14
    ighbor
    0.14
    iosis
    0.14
     trade
    0.14
     Decomp
    0.14
    acement
    0.14
     Interr
    0.13
     trif
    0.13
    Act Density 0.007%

    No Known Activations