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

    Neuronpedia

    INDEX
    Explanations

    references to shared values and collaboration among groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lier
    -0.22
     Crush
    -0.19
    uars
    -0.17
    adin
    -0.15
     merch
    -0.15
     Grat
    -0.15
    öt
    -0.14
    ensch
    -0.14
     Kurd
    -0.14
    ombo
    -0.14
    POSITIVE LOGITS
    /Common
    0.17
    åĬ¡
    0.16
    /shared
    0.16
    941
    0.15
    åĭĻ
    0.15
    ertz
    0.14
     common
    0.14
    985
    0.14
    psc
    0.14
    esso
    0.14
    Act Density 0.113%

    No Known Activations