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

    Neuronpedia

    INDEX
    Explanations

    questions related to direction and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     possession
    -0.15
    OLLOW
    -0.15
     QSize
    -0.15
    istle
    -0.15
    474
    -0.14
    astle
    -0.14
    boru
    -0.14
     possessed
    -0.14
     Sadd
    -0.14
     possess
    -0.13
    POSITIVE LOGITS
     headed
    0.23
     hiding
    0.19
     located
    0.18
    located
    0.18
     hide
    0.17
     fit
    0.17
     hid
    0.17
    -hide
    0.17
     ÙĤرار
    0.17
     Äijứng
    0.17
    Act Density 0.102%

    No Known Activations