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

    Neuronpedia

    INDEX
    Explanations

    the word "As" indicating the start of explanations or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     evidenced
    -0.16
    ugs
    -0.15
    ired
    -0.15
    ovation
    -0.15
    ession
    -0.14
    cision
    -0.14
     bulk
    -0.14
    isé
    -0.13
    mes
    -0.13
    .djangoproject
    -0.13
    POSITIVE LOGITS
    ereotype
    0.16
    ward
    0.16
    ãĥ¼ãĥ«
    0.15
    až
    0.15
    ocz
    0.15
     Boeh
    0.15
    BufferData
    0.14
    ynchronously
    0.14
    acus
    0.14
    arde
    0.14
    Act Density 0.071%

    No Known Activations