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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or groups, particularly in the context of judgment or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wilber
    -0.85
    ocarp
    -0.81
     écou
    -0.78
    laps
    -0.76
    Nag
    -0.73
     Mep
    -0.72
     MEG
    -0.70
     SNA
    -0.69
     Fascism
    -0.69
     Nag
    -0.69
    POSITIVE LOGITS
     those
    1.60
    Those
    1.37
    those
    1.35
     Those
    1.32
     THOSE
    1.16
     who
    1.12
     ceux
    1.07
     aquellos
    1.03
    那些
    0.95
     aqueles
    0.95
    Act Density 0.081%

    No Known Activations