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

    Neuronpedia

    INDEX
    Explanations

    expressions related to conflict and resistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.17
     “âĢ¦
    -0.15
    bject
    -0.14
    ä¼¼ä¹İ
    -0.14
    //*[
    -0.14
    ijke
    -0.13
     /^
    -0.13
    ãĥ¼ãĥĩ
    -0.13
     Magick
    -0.13
    chin
    -0.13
    POSITIVE LOGITS
     [
    0.21
     tomorrow
    0.20
     brothers
    0.17
     Brothers
    0.17
     God
    0.16
     [$
    0.15
    jvu
    0.15
     our
    0.15
    [s
    0.14
     here
    0.14
    Act Density 0.175%

    No Known Activations