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

    Neuronpedia

    INDEX
    Explanations

    references to caves and tunnels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    serter
    -0.16
    æĸĻ
    -0.15
    enberg
    -0.15
    rive
    -0.15
    394
    -0.14
    Globals
    -0.13
     Composition
    -0.13
    ackson
    -0.13
    AKE
    -0.13
    RIA
    -0.13
    POSITIVE LOGITS
     containing
    0.20
    laus
    0.17
     walls
    0.16
    éĩĮ
    0.16
     contain
    0.16
    åĨħ
    0.15
     Svens
    0.15
     doors
    0.15
    ascus
    0.15
    oky
    0.15
    Act Density 0.272%

    No Known Activations