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

    Neuronpedia

    INDEX
    Explanations

    legal and political assertions related to authority and legitimacy

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     himo
    -0.73
    ReusableCell
    -0.66
    findpost
    -0.62
    balleur
    -0.62
     Lightboxes
    -0.59
    awtextra
    -0.59
    Autoritní
    -0.58
    </tfoot>
    -0.57
    aarrggbb
    -0.57
     Exactos
    -0.57
    POSITIVE LOGITS
    __*/
    0.54
    Przypisy
    0.54
     entitled
    0.54
    entitled
    0.53
     bazie
    0.47
    WEBPACK
    0.47
    Einzelnachweise
    0.47
     legally
    0.46
     Mors
    0.46
     technically
    0.45
    Act Density 0.366%

    No Known Activations