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

    Neuronpedia

    INDEX
    Explanations

    instances where something is being filled, such as gaps, roles, positions, voids, or orders

    oai_token-act-pair · gpt-3.5-turbo

    references to filling gaps or vacancies in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conduct
    -0.81
    hess
    -0.66
    hend
    -0.66
    esson
    -0.65
    Ń
    -0.65
     proceed
    -0.63
    saf
    -0.63
    aviour
    -0.62
     Married
    -0.62
     Conduct
    -0.62
    POSITIVE LOGITS
     gaps
    1.54
     void
    1.43
     gap
    1.38
     coffers
    1.34
     vacancies
    1.30
     vacancy
    1.30
     holes
    1.22
     hole
    1.20
     vacuum
    1.17
     slots
    1.16
    Act Density 0.132%

    No Known Activations