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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to consultation or involvement of the general public

    oai_token-act-pair · gpt-3.5-turbo

    references to "people" and their concerns or representation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.83
    BALL
    -0.80
    FIN
    -0.77
    inventoryQuantity
    -0.71
    Va
    -0.71
    Duration
    -0.70
    terday
    -0.69
     srfAttach
    -0.67
    Entry
    -0.67
    LV
    -0.66
    POSITIVE LOGITS
    folk
    1.00
     smugglers
    0.96
    liest
    0.90
     inhab
    0.90
     entrusted
    0.83
     closest
    0.83
     composing
    0.81
    ourced
    0.81
     besie
    0.80
     who
    0.78
    Act Density 0.047%

    No Known Activations