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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and characters formatted like status codes or identifiers

    oai_token-act-pair · gpt-3.5-turbo

    numerical status updates or identifiers related to social media posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nomine
    -0.84
     DRAG
    -0.64
    ¨
    -0.63
     masc
    -0.62
     Belt
    -0.61
     NRA
    -0.60
     successors
    -0.58
     chants
    -0.58
     Vest
    -0.58
    lé
    -0.56
    POSITIVE LOGITS
    806
    1.33
    389
    1.32
    985
    1.32
    768
    1.31
    679
    1.30
    269
    1.30
    406
    1.30
    485
    1.29
    264
    1.29
    405
    1.29
    Act Density 0.047%

    No Known Activations