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

    Neuronpedia

    INDEX
    Explanations

    mentions of family members and relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to family relationships and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auri
    -0.81
    afort
    -0.76
    ãĤ¤ãĥĪ
    -0.71
     ceilings
    -0.71
    clude
    -0.70
    etting
    -0.70
     Pwr
    -0.67
    pex
    -0.67
    æĺ
    -0.67
    ortmund
    -0.66
    POSITIVE LOGITS
    ÃŃs
    0.77
     Sandwich
    0.74
     Geek
    0.68
     Hyde
    0.66
    loo
    0.66
     hooked
    0.66
     todd
    0.66
     Simulator
    0.65
    river
    0.64
    friend
    0.62
    Act Density 0.100%

    No Known Activations