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

    Neuronpedia

    INDEX
    Explanations

    phrases concerning user privacy and data security practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     l
    -0.17
     qu
    -0.17
     n
    -0.17
     subs
    -0.16
     y
    -0.16
    it
    -0.15
     al
    -0.15
    e
    -0.15
     ing
    -0.15
     submit
    -0.15
    POSITIVE LOGITS
    ersiz
    0.18
    zych
    0.16
    'gc
    0.16
    ponsive
    0.16
     fitte
    0.15
     sperma
    0.15
    ãĤ·ãĥ§
    0.15
     oppon
    0.15
     rencontrer
    0.14
    wner
    0.14
    Act Density 0.055%

    No Known Activations