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

    Neuronpedia

    INDEX
    Explanations

    locations or proper names consisting of uppercase letters

    oai_token-act-pair · gpt-3.5-turbo

    references to cities and organizations, particularly in relation to their activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dn
    -0.69
    course
    -0.68
    venge
    -0.66
     Deep
    -0.66
    Zero
    -0.63
    ãĥĵ
    -0.63
     Notting
    -0.62
    ington
    -0.62
    company
    -0.60
    wave
    -0.60
    POSITIVE LOGITS
     CITY
    1.09
    TIT
    1.08
     IMAGES
    1.06
     DRAG
    1.06
     GOODMAN
    1.05
    IRO
    1.04
    ILA
    1.04
    LAND
    1.00
     EDITION
    1.00
     REPORT
    0.99
    Act Density 0.088%

    No Known Activations