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

    Neuronpedia

    INDEX
    Explanations

    references to box office performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOX
    -0.16
    antu
    -0.15
     Mug
    -0.15
    webtoken
    -0.15
    kw
    -0.14
    ashi
    -0.14
    utor
    -0.14
     trÃŃ
    -0.14
    bert
    -0.14
    urre
    -0.14
    POSITIVE LOGITS
    -office
    0.24
    meer
    0.21
     office
    0.20
    office
    0.20
    ercise
    0.20
    score
    0.19
    _office
    0.19
    scores
    0.18
     Office
    0.18
    Office
    0.17
    Act Density 0.006%

    No Known Activations