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

    Neuronpedia

    INDEX
    Explanations

    references to time and military movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WWII
    -0.20
     colourful
    -0.19
     ‘
    -0.17
     “âĢ¦
    -0.17
     décor
    -0.17
     blackout
    -0.16
     paed
    -0.15
     [âĢ¦]↵↵
    -0.15
    č
    -0.15
     ...↵↵
    -0.14
    POSITIVE LOGITS
     General
    0.20
     Pillow
    0.19
     myself
    0.19
     Battery
    0.19
     my
    0.17
     rebel
    0.17
     Colonel
    0.17
     Numbers
    0.17
     batteries
    0.16
     Chattanooga
    0.16
    Act Density 0.010%

    No Known Activations