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

    Neuronpedia

    INDEX
    Explanations

    locations or related terms such as cities or states

    oai_token-act-pair · gpt-3.5-turbo

    locations, particularly cities and regions in the U.S

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gamma
    -0.65
    uds
    -0.64
     Tempest
    -0.63
    venge
    -0.61
    ãĥł
    -0.61
    bottom
    -0.60
    aults
    -0.59
    istration
    -0.59
    ges
    -0.59
    ginx
    -0.59
    POSITIVE LOGITS
     POL
    1.02
     CITY
    1.01
    INESS
    1.01
     EDITION
    1.00
     IMAGES
    0.97
    MAN
    0.97
     MARK
    0.95
    FIELD
    0.93
    EVA
    0.91
     DEL
    0.89
    Act Density 0.052%

    No Known Activations