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

    Neuronpedia

    INDEX
    Explanations

    words related to spices, specifically 'ginger' as it triggers the strongest activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "ginger"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igslist
    -0.75
    iries
    -0.74
    ktop
    -0.71
    election
    -0.69
    cffffcc
    -0.66
    isites
    -0.65
    innacle
    -0.64
    ingu
    -0.63
    iard
    -0.62
    oln
    -0.62
    POSITIVE LOGITS
    bread
    1.63
     ginger
    1.40
     Ginger
    1.12
     ale
    0.94
    cake
    0.87
    ned
    0.87
    weed
    0.84
    beans
    0.82
    bum
    0.80
    bats
    0.78
    Act Density 0.005%

    No Known Activations