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

    Neuronpedia

    INDEX
    Explanations

    negative words related to behavior or attitudes such as insanity, ignorance, arrogance, and hypocrisy

    oai_token-act-pair · gpt-3.5-turbo

    themes related to mental health issues and societal ignorance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amins
    -0.86
    icles
    -0.82
    icle
    -0.81
    Interstitial
    -0.80
    ergy
    -0.75
    ramer
    -0.73
    ta
    -0.73
    umm
    -0.73
    char
    -0.71
    arers
    -0.71
    POSITIVE LOGITS
     prejudice
    1.03
     intolerance
    0.91
    lessness
    0.89
    yip
    0.88
    xtap
    0.88
    fulness
    0.87
     stupidity
    0.84
     ignorance
    0.84
     malice
    0.82
    ophobia
    0.80
    Act Density 0.051%

    No Known Activations