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

    Neuronpedia

    INDEX
    Explanations

    concepts related to restrictions and limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jev
    -0.17
    kar
    -0.17
    inea
    -0.16
    emes
    -0.15
    cest
    -0.15
    kinson
    -0.15
    ansi
    -0.15
     Dün
    -0.14
     ought
    -0.14
    临
    -0.14
    POSITIVE LOGITS
     scope
    0.28
    limited
    0.21
     limited
    0.21
     Scope
    0.21
     Limited
    0.19
    scope
    0.19
    	scope
    0.19
    limitations
    0.18
    éĻIJ
    0.18
     scopes
    0.18
    Act Density 0.075%

    No Known Activations