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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a transition or change in state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theid
    -0.17
    LOCITY
    -0.15
    urma
    -0.15
    okino
    -0.14
    TouchEvent
    -0.14
    adera
    -0.14
    ishly
    -0.14
    etros
    -0.14
     strSql
    -0.13
    Pocket
    -0.13
    POSITIVE LOGITS
     halt
    0.28
     abrupt
    0.24
     stand
    0.21
     sc
    0.21
     close
    0.20
     grinding
    0.20
    merc
    0.20
     merc
    0.19
     crashing
    0.19
     HAL
    0.19
    Act Density 0.017%

    No Known Activations