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

    Neuronpedia

    INDEX
    Explanations

    references to discussions or conversations on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zink
    -0.63
     Borden
    -0.63
    whelmed
    -0.62
     plomb
    -0.60
    لاثة
    -0.59
     mal
    -0.59
    mal
    -0.58
    rakt
    -0.57
     outta
    -0.57
    googleapis
    -0.56
    POSITIVE LOGITS
     discussion
    1.79
     discussions
    1.59
    discussion
    1.53
     discus
    1.52
     discuss
    1.49
     Discussion
    1.45
     Discussions
    1.43
     Discuss
    1.43
    discussions
    1.41
     DISCUSSION
    1.39
    Act Density 0.098%

    No Known Activations