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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "leaf"

    oai_token-act-pair · gpt-3.5-turbo

    references to leaves or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alty
    -0.69
    éŃĶ
    -0.67
    anyahu
    -0.65
     incumb
    -0.63
    verbal
    -0.62
    ammy
    -0.62
    duction
    -0.62
    ativity
    -0.61
    PDATE
    -0.61
     attackers
    -0.61
    POSITIVE LOGITS
    let
    1.17
    lets
    1.06
     leaf
    1.04
    leaf
    1.01
    leted
    0.92
     lettuce
    0.86
    ife
    0.82
    worm
    0.81
    edIn
    0.81
    ier
    0.80
    Act Density 0.022%

    No Known Activations