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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters resembling proper names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    581
    -0.15
    ray
    -0.14
    pez
    -0.14
     zbo
    -0.14
     kans
    -0.14
    обов
    -0.13
    neau
    -0.13
    erif
    -0.13
    illac
    -0.13
    andering
    -0.13
    POSITIVE LOGITS
     Clipboard
    0.15
    uchi
    0.14
    »
    0.14
    oeff
    0.14
    idge
    0.14
    TRS
    0.14
    #af
    0.14
    ullet
    0.14
     Tas
    0.13
    lov
    0.13
    Act Density 0.029%

    No Known Activations