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

    Neuronpedia

    INDEX
    Explanations

    references to trust or entities associated with trust

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erva
    -0.16
     ë§ī
    -0.15
    Stars
    -0.15
    fragistics
    -0.15
    ipi
    -0.15
    _lineno
    -0.14
     bande
    -0.14
    ãĤĩãģĨ
    -0.14
    Ñĥва
    -0.14
    ubar
    -0.14
    POSITIVE LOGITS
    .window
    0.15
     Phelps
    0.14
    unge
    0.14
    xea
    0.14
    ample
    0.14
    uels
    0.13
    .bulk
    0.13
    ̣
    0.13
    uter
    0.13
    itory
    0.13
    Act Density 0.005%

    No Known Activations