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

    Neuronpedia

    INDEX
    Explanations

    commands related to actions or requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymous
    -0.16
    ows
    -0.15
    ampion
    -0.14
    ayed
    -0.14
    BY
    -0.13
    ropolis
    -0.13
    owie
    -0.13
    راÙĨÙĩ
    -0.13
     Invocation
    -0.13
    acker
    -0.13
    POSITIVE LOGITS
     your
    0.33
     yourself
    0.33
     Yourself
    0.31
    ä½łçļĦ
    0.30
     Your
    0.27
    your
    0.27
    Your
    0.26
    ing
    0.25
     yourselves
    0.25
     ваÑĪ
    0.22
    Act Density 0.311%

    No Known Activations