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

    Neuronpedia

    INDEX
    Explanations

    themes related to community responsibility and social engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     extents
    -0.17
    innie
    -0.16
    agment
    -0.15
    ÅĤe
    -0.15
     extent
    -0.15
    eldon
    -0.14
    hem
    -0.14
    rics
    -0.14
    prises
    -0.14
    ernen
    -0.14
    POSITIVE LOGITS
    ìĬ¤íħĮ
    0.15
    åķ
    0.14
    ToF
    0.14
    atre
    0.14
    ãĥ¼ãĥĭ
    0.14
     proper
    0.14
    δα
    0.13
    aley
    0.13
    proper
    0.13
    ALSE
    0.13
    Act Density 0.396%

    No Known Activations