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

    Neuronpedia

    INDEX
    Explanations

    terms related to social concepts and their underlying structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anoia
    -0.18
    ãĤ£
    -0.17
    ancode
    -0.16
    iki
    -0.15
    utow
    -0.15
    apolis
    -0.15
    edList
    -0.14
    eday
    -0.14
    bih
    -0.14
    asto
    -0.14
    POSITIVE LOGITS
     superf
    0.14
    nes
    0.14
    oles
    0.14
     Ud
    0.13
    oren
    0.13
    _foreign
    0.13
    olio
    0.13
    _MPI
    0.13
     investig
    0.13
    otten
    0.13
    Act Density 0.005%

    No Known Activations