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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "stop" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢив
    -0.16
    ensing
    -0.15
    urally
    -0.15
    tos
    -0.15
    iÃŁ
    -0.15
    ichten
    -0.15
    дав
    -0.15
    ts
    -0.14
    ating
    -0.14
    stride
    -0.14
    POSITIVE LOGITS
    page
    0.27
    gap
    0.26
    per
    0.26
    lights
    0.25
    pered
    0.25
    -motion
    0.24
    /start
    0.24
    over
    0.23
    PING
    0.21
    overs
    0.21
    Act Density 0.022%

    No Known Activations