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

    Neuronpedia

    INDEX
    Explanations

    food-related words

    oai_token-act-pair · gpt-3.5-turbo

    specific food items and scientific terms related to health and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pak
    -0.73
     RH
    -0.69
     KR
    -0.68
     NJ
    -0.63
     TW
    -0.63
     VID
    -0.62
     CB
    -0.62
    Nap
    -0.61
     NC
    -0.61
     NEC
    -0.61
    POSITIVE LOGITS
    sers
    0.75
    olean
    0.74
    tml
    0.74
    igger
    0.72
    eers
    0.68
    osate
    0.67
    ernel
    0.67
    forcement
    0.66
    vertising
    0.66
    ̶
    0.66
    Act Density 0.255%

    No Known Activations