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

    Neuronpedia

    INDEX
    Explanations

    the word "Plus" and its variations, indicating an additive or additional context in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tube
    -0.17
    eer
    -0.16
    nt
    -0.15
    ize
    -0.15
    INSTANCE
    -0.14
    asthan
    -0.14
    igo
    -0.14
    WER
    -0.14
    ube
    -0.13
    بس
    -0.13
    POSITIVE LOGITS
    ieurs
    0.21
    -minus
    0.18
    quam
    0.17
    ++++++++++++++++++++++++++++++++
    0.17
    vier
    0.17
     sclerosis
    0.16
     ça
    0.15
    ÑĶм
    0.15
    vrier
    0.15
    lector
    0.14
    Act Density 0.020%

    No Known Activations