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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote a halt or pause in progress or activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urma
    -0.15
    theid
    -0.15
    ustos
    -0.14
    TouchEvent
    -0.14
    adera
    -0.14
    kiem
    -0.14
    ongo
    -0.14
    CHIP
    -0.14
    ICTURE
    -0.14
    adoo
    -0.14
    POSITIVE LOGITS
     halt
    0.29
     close
    0.27
     sc
    0.25
     abrupt
    0.24
     grinding
    0.24
     stand
    0.23
     crawl
    0.21
     ing
    0.20
     crashing
    0.19
     boil
    0.19
    Act Density 0.017%

    No Known Activations