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

    Neuronpedia

    INDEX
    Explanations

    terms associated with strictness or rigidity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÐIJÑĢÑħÑĸв
    -0.16
    rtl
    -0.15
    mun
    -0.15
    _CHIP
    -0.15
    QUIRED
    -0.14
     cigaret
    -0.14
    ãģ£ãģ¨
    -0.14
    utomation
    -0.14
    arring
    -0.14
    RTL
    -0.14
    POSITIVE LOGITS
     in
    0.16
     B
    0.15
    0.15
     Brun
    0.14
     and
    0.14
     on
    0.14
    geries
    0.14
    -
    0.14
     T
    0.14
    -l
    0.14
    Act Density 0.016%

    No Known Activations