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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the source or origin of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    بار
    -0.17
    erland
    -0.16
    lej
    -0.16
    hani
    -0.16
    vice
    -0.15
    VICE
    -0.15
    RDD
    -0.15
    सà¤Ń
    -0.15
    vfs
    -0.14
    arkan
    -0.14
    POSITIVE LOGITS
    0.18
     أجÙĦ
    0.14
     Blaze
    0.14
    imoto
    0.14
     http
    0.14
    idelity
    0.14
     placement
    0.14
    è¦ļ
    0.14
    anch
    0.14
    ures
    0.13
    Act Density 0.002%

    No Known Activations