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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive language reflecting personal relationships and community sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latine
    -0.67
     înc
    -0.65
     numele
    -0.64
     învă
    -0.60
     aveug
    -0.60
     afstand
    -0.56
     decât
    -0.54
     întâ
    -0.53
    likelihood
    -0.52
     împre
    -0.51
    POSITIVE LOGITS
    aarrggbb
    0.77
     مشين
    0.75
    TemporalType
    0.73
    ViewFeatures
    0.67
     صوتيه
    0.66
    LayoutStyle
    0.66
     المعيارى
    0.64
    Tembelea
    0.64
    sizeCache
    0.63
    Vidite
    0.62
    Act Density 0.152%

    No Known Activations