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

    Neuronpedia

    INDEX
    Explanations

    information related to controversial topics and debates

    oai_token-act-pair · gpt-3.5-turbo

    assertions or beliefs about significant historical or political events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     summarizes
    -0.56
    cellaneous
    -0.52
    swick
    -0.52
    bilt
    -0.51
     partName
    -0.49
    wrapper
    -0.49
    ãĤ´ãĥ³
    -0.48
    inis
    -0.48
    adel
    -0.47
    ogether
    -0.46
    POSITIVE LOGITS
     unfairly
    0.65
     unconstitutional
    0.62
     imminent
    0.60
     beneficial
    0.59
     racist
    0.59
    "))
    0.57
     harmful
    0.57
     plagiar
    0.55
     sexist
    0.55
     pedoph
    0.55
    Act Density 1.486%

    No Known Activations