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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific items or details within a text

    oai_token-act-pair · gpt-3.5-turbo

    elements related to documentation and references in articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elsius
    -0.73
    upiter
    -0.67
    guyen
    -0.65
    ynchron
    -0.63
    bestos
    -0.62
    atism
    -0.59
    ationally
    -0.59
    coni
    -0.59
    planet
    -0.58
    ccording
    -0.58
    POSITIVE LOGITS
     booklet
    0.82
     section
    0.81
     accompanying
    0.81
    notes
    0.75
     filings
    0.74
     acknowled
    0.74
     context
    0.74
     pamphlet
    0.72
     onwards
    0.71
     roundup
    0.71
    Act Density 0.391%

    No Known Activations