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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparison or opposition (e.g., "good vs evil", "high vs low sensitivity")

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and prepositions indicating relationships or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.69
    nen
    -0.69
    Players
    -0.68
    illac
    -0.64
     Cosponsors
    -0.63
     sugg
    -0.62
     condem
    -0.62
     misunder
    -0.62
    elle
    -0.61
    Uncommon
    -0.61
    POSITIVE LOGITS
     infinity
    0.73
     lowly
    0.72
     emptiness
    0.64
     messenger
    0.63
     minus
    0.63
     voic
    0.63
     decay
    0.63
     suffix
    0.61
     math
    0.60
     multiply
    0.60
    Act Density 0.333%

    No Known Activations