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

    Neuronpedia

    INDEX
    Explanations

    expressions that emphasize significant topics or concepts in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Witt
    -0.16
    ÑĨÑĥ
    -0.14
     j
    -0.14
    .logic
    -0.14
     ret
    -0.14
    ảm
    -0.14
    ัม
    -0.14
    ylene
    -0.13
     sát
    -0.13
    iddi
    -0.13
    POSITIVE LOGITS
    eland
    0.18
    bic
    0.15
    ç¾
    0.15
    urd
    0.15
    ensen
    0.14
    UBLE
    0.14
    ect
    0.14
    ToDevice
    0.14
    wind
    0.14
     independence
    0.14
    Act Density 0.000%

    No Known Activations