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

    Neuronpedia

    INDEX
    Explanations

    references to specific universities and their programs or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Headquarters
    -0.16
     Universities
    -0.15
    ãĥĹãĥ¬
    -0.15
    ãĤ¤ãĥĪ
    -0.15
    uss
    -0.14
    Membership
    -0.14
     apprent
    -0.14
    .documentation
    -0.14
    æĦ
    -0.13
    addock
    -0.13
    POSITIVE LOGITS
    .edu
    0.23
     Extension
    0.21
     Libraries
    0.20
     prof
    0.19
     Law
    0.19
     professor
    0.19
    prof
    0.18
     commencement
    0.18
     Prov
    0.18
     alum
    0.17
    Act Density 0.112%

    No Known Activations