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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ranking or position at the top of a list

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignite
    -0.15
    inness
    -0.15
     Johann
    -0.14
    oint
    -0.14
    lip
    -0.13
    imals
    -0.13
    itti
    -0.13
    plied
    -0.13
    obby
    -0.13
    ugu
    -0.13
    POSITIVE LOGITS
     Carrier
    0.16
    ãĤªãĥª
    0.15
    leta
    0.15
    ¿ł
    0.14
    opup
    0.14
    undo
    0.14
    .gdx
    0.14
    viso
    0.13
    ãĥ¬ãĤ¹
    0.13
    OKIE
    0.13
    Act Density 0.040%

    No Known Activations