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

    Neuronpedia

    INDEX
    Explanations

    references to the city of San Francisco

    oai_token-act-pair · gpt-3.5-turbo

    city names and specific locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¨ãĥ«
    -0.76
    ãĥķãĤ©
    -0.66
    è£ħ
    -0.63
    ãĥ¼ãĤ¯
    -0.63
    ãĥ¡
    -0.63
    Gender
    -0.63
    xual
    -0.62
    ãĥīãĥ©ãĤ´ãĥ³
    -0.60
    ãĤ¶
    -0.59
    ãĤ¹ãĥĪ
    -0.57
    POSITIVE LOGITS
     Lambert
    0.64
    vey
    0.62
    amate
    0.60
    atton
    0.58
    NESS
    0.57
    telling
    0.56
    heit
    0.54
    reciation
    0.53
    lege
    0.53
    ilon
    0.53
    Act Density 0.590%

    No Known Activations