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

    Neuronpedia

    INDEX
    Explanations

    controversial or divisive topics and terms related to social and political issues

    oai_token-act-pair · gpt-3.5-turbo

    references to current political issues and controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ´
    -0.61
    ä
    -0.59
    ãĤ·ãĥ£
    -0.55
    é¾įå
    -0.55
     Seas
    -0.54
    cellaneous
    -0.52
    ŃĶ
    -0.51
    named
    -0.51
    YN
    -0.51
    Hur
    -0.49
    POSITIVE LOGITS
     anymore
    0.78
     anytime
    0.73
     someday
    0.72
     sooner
    0.69
     legitimately
    0.66
    matically
    0.64
     instead
    0.64
     differently
    0.64
     ASAP
    0.64
    *****
    0.60
    Act Density 1.193%

    No Known Activations