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

    Neuronpedia

    INDEX
    Explanations

    references to medical conditions or equipment

    oai_token-act-pair · gpt-3.5-turbo

    references to maternity and paternity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    meric
    -0.86
    yssey
    -0.84
    edIn
    -0.79
    edo
    -0.76
    leys
    -0.75
    ed
    -0.75
    er
    -0.74
    lies
    -0.73
    istan
    -0.71
    atile
    -0.70
    POSITIVE LOGITS
    ãĥ¤
    0.76
    ãĥ³ãĤ¸
    0.74
    plates
    0.71
    otine
    0.71
    udeau
    0.69
    ãĤª
    0.69
     depreciation
    0.68
     STATES
    0.68
    ãĤº
    0.67
    ãĤ¨ãĥ«
    0.67
    Act Density 0.163%

    No Known Activations