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

    Neuronpedia

    INDEX
    Explanations

    empty physical spaces

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "empty."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CVE
    -0.88
    NEWS
    -0.87
    ETA
    -0.81
    Murray
    -0.79
    abol
    -0.78
    egal
    -0.78
    dar
    -0.77
    cko
    -0.76
    Lock
    -0.75
    MSN
    -0.74
    POSITIVE LOGITS
     empty
    0.99
     Empty
    0.90
    empty
    0.83
     souls
    0.81
     blank
    0.79
     emptiness
    0.79
     placeholder
    0.77
     spaces
    0.74
     vacancies
    0.74
     emptied
    0.73
    Act Density 0.009%

    No Known Activations