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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly related to legal cases, judgments, and medical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lafayette
    -1.00
     Sine
    -0.94
    Sine
    -0.84
     Theodo
    -0.79
    didSet
    -0.79
     Ebenezer
    -0.79
     Yvette
    -0.78
     Presbyter
    -0.76
     ônibus
    -0.76
     Rosetta
    -0.75
    POSITIVE LOGITS
     Ramirez
    0.77
    ]";
    0.76
    fjord
    0.72
    ■■
    0.72
     quoi
    0.72
     gars
    0.69
     Boas
    0.68
     Musa
    0.68
     tat
    0.68
    pogon
    0.67
    Act Density 2.287%

    No Known Activations