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

    Neuronpedia

    INDEX
    Explanations

    references to staying or remaining in a location or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cob
    -0.17
     Domestic
    -0.15
     lap
    -0.15
    ol
    -0.15
     Hugo
    -0.14
    rol
    -0.14
    227
    -0.14
     laps
    -0.14
     Hou
    -0.14
    олом
    -0.14
    POSITIVE LOGITS
     longer
    0.27
     Longer
    0.21
     stay
    0.19
    enschaft
    0.17
    stay
    0.17
     stayed
    0.17
     Kaynak
    0.16
    iveau
    0.16
    AspectRatio
    0.16
    ummer
    0.16
    Act Density 0.058%

    No Known Activations