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

    Neuronpedia

    INDEX
    Explanations

    references to action and adventure themes in films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALSE
    -0.17
    ontent
    -0.16
     Telescope
    -0.15
    eteor
    -0.15
    dream
    -0.15
    ds
    -0.14
    aight
    -0.14
     Miner
    -0.14
    edith
    -0.14
    Uvs
    -0.14
    POSITIVE LOGITS
     Vig
    0.17
     Femme
    0.17
     kill
    0.17
     dispatch
    0.16
     hack
    0.16
     carn
    0.16
     sovereign
    0.16
     ticking
    0.16
     Agent
    0.16
     hired
    0.15
    Act Density 0.183%

    No Known Activations