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

    Neuronpedia

    INDEX
    Explanations

    descriptions containing the word "filled"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "filled" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utan
    -0.72
    rf
    -0.71
    isation
    -0.70
    NOR
    -0.70
    practice
    -0.67
    nature
    -0.67
    recogn
    -0.66
    framework
    -0.65
    appro
    -0.64
    won
    -0.64
    POSITIVE LOGITS
     coffers
    0.76
     vacancies
    0.71
    ummer
    0.71
     stadiums
    0.71
     pores
    0.70
    obar
    0.70
     up
    0.70
    ups
    0.69
     shelves
    0.68
     notebooks
    0.67
    Act Density 0.036%

    No Known Activations