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

    Neuronpedia

    INDEX
    Explanations

    references to political entities and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atoon
    -0.16
    431
    -0.15
    addtogroup
    -0.14
    анÑĮ
    -0.14
    forme
    -0.14
    .cfg
    -0.14
    .mods
    -0.14
    LEC
    -0.14
    enler
    -0.14
    ziej
    -0.13
    POSITIVE LOGITS
     Beam
    0.24
    pras
    0.23
     Rat
    0.22
     Fin
    0.22
     beam
    0.21
     Sta
    0.21
     Rates
    0.20
     Gener
    0.20
     Ober
    0.19
    Beam
    0.19
    Act Density 0.024%

    No Known Activations