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

    Neuronpedia

    INDEX
    Explanations

    mentions of leaves

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "leaf" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PDATE
    -0.71
    CLUS
    -0.67
    senal
    -0.65
    alty
    -0.64
    nels
    -0.63
     attackers
    -0.63
    ogene
    -0.62
    afort
    -0.61
    ENTION
    -0.61
     incumb
    -0.60
    POSITIVE LOGITS
    let
    1.29
    lets
    1.19
    leaf
    1.03
    leted
    1.00
    iard
    0.95
     leaf
    0.93
    lete
    0.91
    ho
    0.89
    overs
    0.87
    letes
    0.87
    Act Density 0.046%

    No Known Activations