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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly of individuals and relevant entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nings
    -0.72
     saline
    -0.72
     lockout
    -0.69
    £ı
    -0.65
    ï¸
    -0.65
    à¼
    -0.63
     theft
    -0.63
     Tycoon
    -0.62
     showers
    -0.61
    ãĥ¼ãĥĨ
    -0.61
    POSITIVE LOGITS
    hou
    0.94
    enegger
    0.93
    leton
    0.92
    borough
    0.89
    atari
    0.88
    schild
    0.83
    rov
    0.79
    hani
    0.78
    ront
    0.78
    Leaks
    0.77
    Act Density 0.097%

    No Known Activations