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

    Neuronpedia

    INDEX
    Explanations

    descriptive sentences and transitions in a text

    oai_token-act-pair · gpt-3.5-turbo

    prompts to explore or suggest actions to the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )</
    -0.60
    Interstitial
    -0.58
     helicop
    -0.56
    Downloadha
    -0.54
    KNOWN
    -0.54
    entimes
    -0.53
    Delivery
    -0.53
    Emergency
    -0.52
     carbohyd
    -0.51
    Located
    -0.50
    POSITIVE LOGITS
     empir
    0.79
     empirical
    0.69
     Chomsky
    0.69
     plaus
    0.63
     disingen
    0.63
     conjecture
    0.62
     speculative
    0.62
     excerpt
    0.60
     skepticism
    0.60
     Krugman
    0.60
    Act Density 1.859%

    No Known Activations