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

    Neuronpedia

    INDEX
    Explanations

    references to physical barriers like fences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of fences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olute
    -0.74
     Monetary
    -0.73
    amus
    -0.70
    olitan
    -0.70
    orean
    -0.70
    alg
    -0.69
    entials
    -0.68
     Nir
    -0.67
    ISTER
    -0.66
     Lear
    -0.64
    POSITIVE LOGITS
     fence
    1.33
     fences
    1.07
     fencing
    1.01
     encl
    0.84
     perimeter
    0.83
     crossings
    0.82
     guarding
    0.82
    yard
    0.81
     wart
    0.81
     gates
    0.80
    Act Density 0.014%

    No Known Activations