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

    Neuronpedia

    INDEX
    Explanations

    references to military groups and geopolitical conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HeaderValue
    -0.14
    fuse
    -0.14
     плав
    -0.14
    phia
    -0.14
    jang
    -0.13
     supra
    -0.13
    _formats
    -0.13
     ëĭ¤ìļ´ë°Ľê¸°
    -0.13
    ection
    -0.13
    ction
    -0.13
    POSITIVE LOGITS
     ret
    0.30
     rec
    0.28
     liber
    0.25
     capture
    0.24
     liberation
    0.23
     Liber
    0.23
     Capture
    0.22
     liberated
    0.22
     capturing
    0.22
     push
    0.21
    Act Density 0.054%

    No Known Activations