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

    Neuronpedia

    INDEX
    Explanations

    sentences that assert a definitive statement or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    POSITE
    -0.17
    --
    -0.16
    zenÃŃ
    -0.15
    agli
    -0.15
    erot
    -0.15
    --↵
    -0.15
    ureka
    -0.14
    itch
    -0.14
    mares
    -0.14
    oodoo
    -0.13
    POSITIVE LOGITS
     Saint
    0.18
     event
    0.16
     ticket
    0.16
     tickets
    0.16
     critics
    0.16
     sec
    0.15
    Saint
    0.15
     Critics
    0.15
     secure
    0.15
     Tickets
    0.15
    Act Density 0.000%

    No Known Activations