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

    Neuronpedia

    INDEX
    Explanations

    references to workplace settings and employee interactions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+#
    -0.66
    tvguidetime
    -0.61
    offsetof
    -0.60
    UrlResolution
    -0.58
    ubility
    -0.54
    ########.
    -0.54
     Wikidata
    -0.54
     NCERT
    -0.54
    timewa
    -0.53
    ГЛА
    -0.52
    POSITIVE LOGITS
     office
    0.96
     cowork
    0.93
     kancel
    0.85
     offices
    0.81
    office
    0.79
     Workspace
    0.79
     workspace
    0.78
     Offices
    0.78
     OFFICES
    0.78
     OFFICE
    0.78
    Act Density 0.097%

    No Known Activations