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

    Neuronpedia

    INDEX
    Explanations

    concepts related to power dynamics and representation in scholarship and discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onz
    -0.17
    prov
    -0.15
    inet
    -0.15
    onda
    -0.15
    agy
    -0.14
    ocale
    -0.14
    eki
    -0.14
    theme
    -0.14
    allery
    -0.14
    rame
    -0.14
    POSITIVE LOGITS
     disc
    0.19
     Scalar
    0.17
    spaces
    0.16
    Scalar
    0.15
     noc
    0.15
     UsersController
    0.15
    uffs
    0.15
    ographies
    0.15
     spaces
    0.15
     scalar
    0.14
    Act Density 0.013%

    No Known Activations