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

    Neuronpedia

    INDEX
    Explanations

    phrases related to photography and food preparation

    oai_token-act-pair · gpt-3.5-turbo

    references to food-related processes and health risks associated with its preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.89
    ©¶æ
    -0.74
    ccording
    -0.73
    oday
    -0.73
     Parables
    -0.71
    querque
    -0.70
    edom
    -0.69
     eleph
    -0.67
    foundland
    -0.66
    £ı
    -0.66
    POSITIVE LOGITS
     cy
    0.58
    .'"
    0.55
    '."
    0.54
    ~
    0.53
    âĶĢâĶĢâĶĢâĶĢ
    0.52
     streaks
    0.51
    ...
    0.51
    Spell
    0.51
    ?'"
    0.50
     *
    0.50
    Act Density 0.137%

    No Known Activations