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

    Neuronpedia

    INDEX
    Explanations

    references to religious organizations and security-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anut
    -0.17
    arine
    -0.16
    ãĥ¥
    -0.16
    709
    -0.15
    964
    -0.15
     Seat
    -0.15
    284
    -0.15
     Yue
    -0.15
    acker
    -0.14
    acking
    -0.14
    POSITIVE LOGITS
    ogram
    0.19
    LIKELY
    0.18
    ople
    0.17
    isku
    0.16
    icias
    0.15
    è¥
    0.15
    .jd
    0.15
    GRAM
    0.15
    .firebaseapp
    0.15
    QRST
    0.15
    Act Density 0.002%

    No Known Activations