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

    Neuronpedia

    INDEX
    Explanations

    references to distance or remoteness

    oai_token-act-pair · gpt-3.5-turbo

    references to distant locations or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingen
    -1.05
    umen
    -0.92
    lain
    -0.92
    piracy
    -0.90
    xual
    -0.86
    uid
    -0.83
    leck
    -0.82
    annis
    -0.81
    inse
    -0.81
    udeb
    -0.80
    POSITIVE LOGITS
     distant
    0.87
     cousin
    0.81
     relatives
    0.80
     neighbour
    0.79
     cousins
    0.78
     Pegasus
    0.78
     neighbours
    0.77
     acquaintance
    0.76
     Near
    0.75
     detachment
    0.75
    Act Density 0.018%

    No Known Activations