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

    Neuronpedia

    INDEX
    Explanations

    names of people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.64
    maxwell
    -0.64
    pmwiki
    -0.62
     shroud
    -0.61
    Ö¼
    -0.61
     whale
    -0.61
     bottleneck
    -0.59
     ______
    -0.59
     retard
    -0.59
     mutated
    -0.58
    POSITIVE LOGITS
     interviewer
    0.99
    iann
    0.83
    ileaks
    0.79
    DERR
    0.78
    News
    0.76
     reporter
    0.75
    ij士
    0.74
    Journal
    0.74
    panel
    0.73
    yon
    0.73
    Act Density 0.410%

    No Known Activations