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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors related to moral judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    extremely negative or offensive descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.75
    tagHelperRunner
    -0.72
    ValueStyle
    -0.71
    ImageContext
    -0.70
    leneck
    -0.69
    -0.69
    DockStyle
    -0.69
    Personendaten
    -0.69
    parsedMessage
    -0.67
    IUrlHelper
    -0.65
    POSITIVE LOGITS
     vile
    0.80
     atrocious
    0.79
     disgusting
    0.77
     filthy
    0.72
     appalling
    0.71
     abominable
    0.69
     heinous
    0.68
     horrific
    0.67
     horrendous
    0.66
     despicable
    0.66
    Act Density 0.017%

    No Known Activations