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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to locations and people

    oai_token-act-pair · gpt-3.5-turbo

    phrases that correspond to geographical locations and notable entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fairfax
    -0.82
     âĹı
    -0.82
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
     Waste
    -0.72
     Arlington
    -0.71
    575
    -0.70
     Clemson
    -0.69
    585
    -0.69
     Wast
    -0.69
     privat
    -0.69
    POSITIVE LOGITS
    j
    1.38
    J
    1.33
    jer
    1.17
    Js
    1.17
    JD
    1.16
    jit
    1.15
    ij
    1.12
    jo
    1.12
    ji
    1.10
    je
    1.10
    Act Density 0.153%

    No Known Activations