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

    Neuronpedia

    INDEX
    Explanations

    terms related to political ideologies and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __":
    -0.68
     مرئيه
    -0.59
    sApp
    -0.59
    AccessorTable
    -0.56
    __':
    -0.54
     fallait
    -0.54
    apimachinery
    -0.54
     externes
    -0.54
    esgue
    -0.53
    KURZBESCHREIBUNG
    -0.53
    POSITIVE LOGITS
    ness
    0.57
    towards
    0.56
    lichung
    0.56
     manly
    0.53
    NESS
    0.52
    LinkId
    0.52
     friendliness
    0.50
     phenotypes
    0.50
     masculinity
    0.50
     towards
    0.49
    Act Density 0.587%

    No Known Activations