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

    Neuronpedia

    INDEX
    Explanations

    phrases related to confinement or restriction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipes
    -0.20
    iske
    -0.16
    actics
    -0.15
    anik
    -0.15
    731
    -0.14
    rah
    -0.14
     Dream
    -0.14
    edin
    -0.14
     sint
    -0.14
     Lump
    -0.14
    POSITIVE LOGITS
    IMS
    0.16
    cket
    0.16
    æ¹¾
    0.15
    izoph
    0.15
    eno
    0.15
     |--------------------------------------------------------------------------↵
    0.14
     tight
    0.14
    ezier
    0.14
    ITED
    0.14
    çķ
    0.14
    Act Density 0.059%

    No Known Activations