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

    Neuronpedia

    INDEX
    Explanations

    features related to data immutability and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    765
    -0.15
    ushima
    -0.15
    볬
    -0.15
    _UNUSED
    -0.15
    uhl
    -0.15
    gii
    -0.15
     Artifact
    -0.14
    ains
    -0.14
    ÑĢоÑĤ
    -0.14
    ion
    -0.13
    POSITIVE LOGITS
    igers
    0.16
    DCF
    0.16
    /write
    0.15
    ardu
    0.15
    illac
    0.14
     ç³
    0.14
    ÑıÑī
    0.14
    antro
    0.13
    engkap
    0.13
    semb
    0.13
    Act Density 0.009%

    No Known Activations