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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to organizations or institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to national organizations or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enger
    -0.86
    eva
    -0.80
    heet
    -0.77
    MODE
    -0.76
    ttes
    -0.76
    hou
    -0.74
    ÙĴ
    -0.73
    furt
    -0.72
    76561
    -0.72
    chnology
    -0.71
    POSITIVE LOGITS
     Geographic
    1.11
     Institutes
    0.97
    ity
    0.89
     Institute
    0.86
     Archives
    0.83
     Headquarters
    0.81
     Center
    0.80
    ized
    0.80
     Security
    0.79
     Colleg
    0.78
    Act Density 0.026%

    No Known Activations