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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "published."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recl
    -0.16
    enson
    -0.15
    nis
    -0.15
    vÃŃce
    -0.14
     Dirty
    -0.14
    èĨ
    -0.14
     Raum
    -0.14
    zÄĻ
    -0.14
    uum
    -0.13
     Miami
    -0.13
    POSITIVE LOGITS
    иÑĤов
    0.18
    .xy
    0.15
    .Requires
    0.15
    abra
    0.15
    ikit
    0.14
    afone
    0.14
    اجر
    0.14
    anca
    0.14
    .dtd
    0.14
    วรร
    0.14
    Act Density 0.009%

    No Known Activations