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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific cases or instances being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wass
    -0.16
    Kir
    -0.15
    ÄĻż
    -0.14
    owler
    -0.14
    erable
    -0.14
    igest
    -0.14
    eller
    -0.14
    ingly
    -0.13
    arium
    -0.13
     Kir
    -0.13
    POSITIVE LOGITS
    icular
    0.17
    >Main
    0.15
    Disclaimer
    0.15
    -ci
    0.14
    ìĦŃ
    0.14
    instance
    0.13
     merely
    0.13
     giy
    0.13
     Gros
    0.13
    aycast
    0.13
    Act Density 0.039%

    No Known Activations