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

    Neuronpedia

    INDEX
    Explanations

    the word "ica" with various prefixes

    oai_token-act-pair · gpt-3.5-turbo

    references to "I" or "we" in the context of identity or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    down
    -0.71
    itarian
    -0.71
     vested
    -0.70
    stroke
    -0.68
    headed
    -0.68
    share
    -0.67
    unders
    -0.67
    affected
    -0.65
     busiest
    -0.65
    downs
    -0.64
    POSITIVE LOGITS
    ica
    1.30
    emia
    1.21
     Rica
    0.99
    ahu
    0.94
     Reborn
    0.93
    ption
    0.90
    iah
    0.87
    ican
    0.85
    odon
    0.84
     Juda
    0.81
    Act Density 0.007%

    No Known Activations