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

    Neuronpedia

    INDEX
    Explanations

    actions related to stopping or pausing activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŃc
    -0.16
    opoulos
    -0.15
    imdi
    -0.15
    vala
    -0.14
    zp
    -0.14
    cke
    -0.14
    zik
    -0.14
    anel
    -0.14
     cent
    -0.14
    ceph
    -0.14
    POSITIVE LOGITS
    STOP
    0.19
     stops
    0.19
    stopped
    0.18
    -stop
    0.18
    stop
    0.18
    711
    0.17
     STOP
    0.17
     stop
    0.17
     Stop
    0.16
     stopped
    0.16
    Act Density 0.042%

    No Known Activations