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

    Neuronpedia

    INDEX
    Explanations

    terms related to geographical locations or specific place names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific ethnic groups and related geopolitical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     undermin
    -0.53
     attRot
    -0.52
    âĹ¼
    -0.52
     psychiat
    -0.52
    $.
    -0.51
    âĵĺ
    -0.49
     behav
    -0.49
     nodd
    -0.49
    issance
    -0.48
     latter
    -0.48
    POSITIVE LOGITS
     [+
    0.61
     [-
    0.61
     ·
    0.60
     [/
    0.60
     |
    0.57
    escription
    0.55
     *)
    0.54
     |--
    0.53
     ->
    0.52
     âĻ
    0.52
    Act Density 0.924%

    No Known Activations