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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating restrictions or permissions regarding actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aday
    -0.15
    OA
    -0.14
    asury
    -0.14
     Norris
    -0.14
    igne
    -0.14
    Threshold
    -0.14
    IOR
    -0.14
    957
    -0.14
     Threshold
    -0.14
    çĭIJ
    -0.14
    POSITIVE LOGITS
     any
    0.18
    ÑģÑĤан
    0.17
    å¾
    0.15
    utow
    0.14
    sure
    0.14
    ÑģÑĤав
    0.14
    ureau
    0.14
    -any
    0.14
     ever
    0.14
    é³¥
    0.14
    Act Density 0.329%

    No Known Activations