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

    Neuronpedia

    INDEX
    Explanations

    phrases related to things that are concealed or occur out of plain sight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etz
    -0.17
    ét
    -0.15
    ẹp
    -0.15
     üzerinden
    -0.15
    enga
    -0.15
     sobie
    -0.15
    eros
    -0.15
    anky
    -0.15
    bedPane
    -0.14
    shal
    -0.14
    POSITIVE LOGITS
     closed
    0.33
    -the
    0.28
     schedule
    0.28
     Closed
    0.27
    s
    0.26
    closed
    0.24
    Closed
    0.24
     bars
    0.23
     Enemy
    0.23
     Bars
    0.22
    Act Density 0.019%

    No Known Activations