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

    Neuronpedia

    INDEX
    Explanations

    references to boundaries or limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rish
    -0.16
    ownik
    -0.16
    rone
    -0.16
    awns
    -0.15
    جاÙĨ
    -0.14
    tod
    -0.14
     erm
    -0.14
    ataires
    -0.14
    üss
    -0.14
    ableView
    -0.14
    POSITIVE LOGITS
     bounds
    0.39
     confines
    0.38
     framework
    0.33
     boundaries
    0.32
     frame
    0.28
     scope
    0.27
    framework
    0.27
     ambit
    0.27
     limits
    0.27
     walls
    0.26
    Act Density 0.149%

    No Known Activations