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

    Neuronpedia

    INDEX
    Explanations

    high-frequency prepositions and associated grammatical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nte
    -0.15
     Kirby
    -0.15
     ancor
    -0.14
    .mods
    -0.14
    ble
    -0.14
    itic
    -0.14
     Edge
    -0.14
    ãĥĥãĤ«ãĥ¼
    -0.14
    imbus
    -0.14
    adj
    -0.14
    POSITIVE LOGITS
    ostel
    0.16
    ktop
    0.15
     Lanc
    0.15
    235
    0.15
    ileÅŁ
    0.15
    @brief
    0.14
    uela
    0.14
     frauen
    0.14
    @",
    0.13
     Heller
    0.13
    Act Density 0.001%

    No Known Activations