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

    Neuronpedia

    INDEX
    Explanations

    instances of a specific character or symbol within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behaviors
    -0.20
     rumor
    -0.17
     neighbors
    -0.17
     CENTER
    -0.17
     harbor
    -0.17
     neighbor
    -0.17
     Flavor
    -0.16
     rumors
    -0.16
     honored
    -0.16
     honor
    -0.16
    POSITIVE LOGITS
     global
    0.18
     personalised
    0.18
    isers
    0.17
     international
    0.17
     OT
    0.16
     Western
    0.16
     travelling
    0.16
    international
    0.16
     fusion
    0.15
    Western
    0.15
    Act Density 0.005%

    No Known Activations