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

    Neuronpedia

    INDEX
    Explanations

    URLs or references to Twitter related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gim
    -0.20
     gre
    -0.15
    uest
    -0.15
     ping
    -0.15
    над
    -0.15
     Gaines
    -0.14
    URING
    -0.14
    gre
    -0.14
     coun
    -0.14
     mating
    -0.14
    POSITIVE LOGITS
    ãĥ³ãĥĦ
    0.15
    orch
    0.15
    wind
    0.14
    MethodInfo
    0.14
    ati
    0.14
    ramid
    0.14
     lá»ĩ
    0.14
    ÅĻes
    0.14
    rance
    0.14
    ROTO
    0.14
    Act Density 0.002%

    No Known Activations