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

    Neuronpedia

    INDEX
    Explanations

    instructions or calls to action with the phrase "be sure to"

    oai_token-act-pair · gpt-3.5-turbo

    instructions or prompts urging the reader to take specific actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ELD
    -0.81
     Haram
    -0.76
    grounds
    -0.73
    lot
    -0.67
    ihad
    -0.66
    Sold
    -0.65
    Qaida
    -0.63
     Confeder
    -0.62
    hent
    -0.61
    pires
    -0.61
    POSITIVE LOGITS
     keep
    1.00
     revisit
    0.99
     indulge
    0.99
     adhere
    0.98
     refresh
    0.97
     avoid
    0.95
     educate
    0.94
     dispel
    0.94
     provide
    0.93
     remember
    0.91
    Act Density 0.092%

    No Known Activations