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

    Neuronpedia

    INDEX
    Explanations

    concepts related to boundaries and limitations, particularly in a societal or cultural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unct
    -0.16
    è³¢
    -0.14
    angkan
    -0.14
    unkt
    -0.14
    IPH
    -0.14
    reff
    -0.14
    ãĥ³ãĥĩãĤ£
    -0.14
    üss
    -0.13
    iam
    -0.13
     æĻ´
    -0.13
    POSITIVE LOGITS
     bounds
    0.60
     boundaries
    0.58
     confines
    0.51
     borders
    0.47
     scope
    0.46
     walls
    0.46
     limits
    0.45
     parameters
    0.41
     ambit
    0.40
    bounds
    0.40
    Act Density 0.214%

    No Known Activations