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

    Neuronpedia

    INDEX
    Explanations

    references to box office performance and related metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOX
    -0.18
    urre
    -0.17
     Mug
    -0.16
    ashi
    -0.15
    वर
    -0.15
    ith
    -0.15
    auce
    -0.15
    zon
    -0.14
    vant
    -0.14
    ceb
    -0.14
    POSITIVE LOGITS
     office
    0.68
    -office
    0.61
    office
    0.61
     Office
    0.59
    Office
    0.56
    _office
    0.54
     offices
    0.48
    åĬŀåħ¬
    0.45
     Offices
    0.41
    .office
    0.41
    Act Density 0.009%

    No Known Activations