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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enschaft
    -0.15
    enny
    -0.15
    ula
    -0.14
    ×IJ
    -0.14
    deaux
    -0.14
    erville
    -0.13
    antan
    -0.13
    Ali
    -0.13
     Ali
    -0.13
    .uni
    -0.13
    POSITIVE LOGITS
    ¬¸
    0.17
    egie
    0.17
    erer
    0.15
    ummings
    0.15
    dae
    0.14
    reated
    0.13
    ¼
    0.13
    esub
    0.13
    alendar
    0.13
    ATTLE
    0.13
    Act Density 1.285%

    No Known Activations