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

    Neuronpedia

    INDEX
    Explanations

    limitations and restrictions in choices or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzzi
    -0.15
     sinking
    -0.15
     zach
    -0.15
    _FAR
    -0.14
    rega
    -0.14
    rella
    -0.14
    ÑģÑĤав
    -0.13
    stab
    -0.13
    _PROP
    -0.13
    ë©´
    -0.13
    POSITIVE LOGITS
     limited
    0.41
    limited
    0.39
     restricted
    0.34
    Limited
    0.31
     only
    0.31
     Limited
    0.30
    æľīéĻIJ
    0.29
     limitations
    0.29
    restricted
    0.29
    Restricted
    0.28
    Act Density 0.189%

    No Known Activations