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

    Neuronpedia

    INDEX
    Explanations

    words related to locations, museums, and sources of information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'museum' or related contexts discussing museums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     millenn
    -0.73
    iter
    -0.69
    olas
    -0.68
    Foot
    -0.66
    kef
    -0.64
     comprom
    -0.63
    uder
    -0.63
     Beir
    -0.63
    obbies
    -0.62
    ensical
    -0.62
    POSITIVE LOGITS
    ::::::::
    0.95
    ,,,,,,,,
    0.92
    ::::
    0.90
    ,,,,
    0.86
    taboola
    0.83
    then
    0.77
    tel
    0.76
    Pa
    0.74
    ;;;;;;;;
    0.71
    ãĥŁ
    0.68
    Act Density 0.043%

    No Known Activations