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

    Neuronpedia

    INDEX
    Explanations

    references to something far away or remote

    oai_token-act-pair · gpt-3.5-turbo

    references to things that are far away or remote

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingen
    -1.02
    lain
    -0.95
    udeb
    -0.93
    umen
    -0.89
    ickson
    -0.87
    ounce
    -0.85
    inse
    -0.84
    annis
    -0.84
    amacare
    -0.81
    leck
    -0.81
    POSITIVE LOGITS
     distant
    0.93
     relatives
    0.88
     cousin
    0.86
     horizon
    0.82
     cousins
    0.82
     Territories
    0.81
     neighbour
    0.79
     neighbours
    0.78
     limb
    0.78
     detachment
    0.76
    Act Density 0.038%

    No Known Activations