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

    Neuronpedia

    INDEX
    Explanations

    various mentions of onions, often with different preparations or pairings in recipes

    oai_token-act-pair · gpt-3.5-turbo

    references to onions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ting
    -0.95
    tered
    -0.88
    brate
    -0.82
    ters
    -0.81
    brates
    -0.77
    TER
    -0.75
    rolled
    -0.75
    ted
    -0.71
    tering
    -0.71
    orah
    -0.70
    POSITIVE LOGITS
     Router
    0.81
    urst
    0.77
    nect
    0.72
    ality
    0.72
    ists
    0.71
    istic
    0.70
    istically
    0.70
    ist
    0.69
    stick
    0.68
    ature
    0.66
    Act Density 0.082%

    No Known Activations