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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "standing" and related phrases suggesting stability or being stationary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sit
    -0.38
     sitting
    -0.34
     Sit
    -0.33
     Sitting
    -0.31
     sits
    -0.29
    Sit
    -0.26
    sit
    -0.25
     seated
    -0.24
     sat
    -0.23
    åĿIJåľ¨
    -0.23
    POSITIVE LOGITS
     outside
    0.20
     near
    0.19
     lookout
    0.16
    Near
    0.16
     Near
    0.16
    lund
    0.15
    outside
    0.15
    near
    0.14
    ษ
    0.14
    anan
    0.14
    Act Density 0.021%

    No Known Activations