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

    Neuronpedia

    INDEX
    Explanations

    phrases related to thin films

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "thin" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pheus
    -0.74
    NL
    -0.68
    bucks
    -0.67
    ILLE
    -0.67
    OUP
    -0.67
    udeau
    -0.66
    ilee
    -0.65
    Particip
    -0.65
    andise
    -0.65
    eering
    -0.64
    POSITIVE LOGITS
    ned
    1.36
    ning
    1.23
    ners
    1.14
    nesses
    0.99
    ened
    0.89
    bread
    0.87
     slices
    0.86
    med
    0.83
    ening
    0.83
     thin
    0.82
    Act Density 0.015%

    No Known Activations