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

    Neuronpedia

    INDEX
    Explanations

    words related to restructuring or destruction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to destruction and structural collapse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leone
    -0.72
    >>>>>>>>
    -0.64
     Wilde
    -0.59
    pora
    -0.57
     background
    -0.56
     steep
    -0.56
     metab
    -0.55
     Alban
    -0.55
     Krishna
    -0.54
     referen
    -0.54
    POSITIVE LOGITS
    ures
    1.19
    ured
    1.03
    ruct
    1.02
    ible
    0.99
    ibles
    0.99
    ural
    0.97
    urally
    0.95
    uring
    0.94
    urous
    0.86
    alore
    0.86
    Act Density 0.032%

    No Known Activations