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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical barriers or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    references to barriers, both physical and metaphorical

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivery
    -0.90
    phis
    -0.82
    matically
    -0.74
    ories
    -0.73
    ergy
    -0.72
    lihood
    -0.72
    sch
    -0.71
    ribution
    -0.71
    ores
    -0.69
    aleb
    -0.68
    POSITIVE LOGITS
     barriers
    1.11
     barrier
    1.03
     erected
    0.97
     separating
    0.92
     walls
    0.88
    buster
    0.85
     Barrier
    0.80
     wall
    0.80
     Walls
    0.80
     crossings
    0.77
    Act Density 0.032%

    No Known Activations