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

    Neuronpedia

    INDEX
    Explanations

    capitalized words related to traditional practices or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to traditional concepts or practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellen
    -0.77
     buckle
    -0.68
    oop
    -0.67
     seat
    -0.67
    assing
    -0.67
    SPONSORED
    -0.66
    ffee
    -0.66
    supp
    -0.64
     commissioner
    -0.63
     glance
    -0.63
    POSITIVE LOGITS
     Traditional
    0.96
    ivation
    0.92
    urally
    0.92
    itionally
    0.91
    Traditional
    0.90
    ertation
    0.88
    hedral
    0.83
    hester
    0.81
    irtual
    0.80
    imates
    0.79
    Act Density 0.011%

    No Known Activations