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

    Neuronpedia

    INDEX
    Explanations

    recurrent phrases related to persistence or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /from
    -0.17
    unas
    -0.16
    hog
    -0.16
    ÑĪÑĥ
    -0.16
    hood
    -0.15
    аÑĢ
    -0.14
    /or
    -0.14
    illery
    -0.13
    osten
    -0.13
    arel
    -0.13
    POSITIVE LOGITS
     pace
    0.21
    .readString
    0.16
    ish
    0.16
    ake
    0.15
    iness
    0.15
    ahan
    0.15
     tabs
    0.15
    AKE
    0.15
    _alive
    0.15
    ellar
    0.14
    Act Density 0.058%

    No Known Activations