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

    Neuronpedia

    INDEX
    Explanations

    pieces of information or updates in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the receipt of information or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dominated
    -0.68
    roying
    -0.66
    cffff
    -0.65
    ournament
    -0.65
    usterity
    -0.63
     offend
    -0.62
    Downloadha
    -0.62
     hated
    -0.61
    orship
    -0.61
    erenn
    -0.61
    POSITIVE LOGITS
     confirmation
    1.66
     clarification
    1.53
     information
    1.48
     details
    1.47
     evidence
    1.43
     indications
    1.42
     insight
    1.41
     hints
    1.41
     clues
    1.41
     answers
    1.40
    Act Density 0.403%

    No Known Activations