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

    Neuronpedia

    INDEX
    Explanations

    terms related to discussions on political conservative viewpoints along with phrases associated with physical medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal beliefs and societal values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.84
    cffffcc
    -0.61
    interstitial
    -0.53
    moon
    -0.53
    kamp
    -0.53
    çīĪ
    -0.52
    emies
    -0.52
    AMY
    -0.51
    Ĥª
    -0.51
    ¬¼
    -0.51
    POSITIVE LOGITS
     slightest
    0.76
     whatsoever
    0.75
    ught
    0.64
     satisfactory
    0.59
     existence
    0.58
    enance
    0.58
     evils
    0.57
     outcome
    0.56
     either
    0.56
     anybody
    0.56
    Act Density 1.101%

    No Known Activations