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

    Neuronpedia

    INDEX
    Explanations

    words related to household appliances

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of appliances and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lot
    -0.77
    bos
    -0.77
    ffiti
    -0.77
    pac
    -0.75
    tering
    -0.72
    nda
    -0.71
    lock
    -0.70
     Pad
    -0.70
    maps
    -0.69
    Po
    -0.69
    POSITIVE LOGITS
     appliance
    0.91
     Appl
    0.82
    itness
    0.74
     appliances
    0.73
     simultane
    0.70
    ^^^^
    0.68
    uous
    0.67
    rador
    0.67
    ^^
    0.67
     transformer
    0.66
    Act Density 0.035%

    No Known Activations