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

    Neuronpedia

    INDEX
    Explanations

    action sentences that involve either hypothetical or speculative scenarios

    oai_token-act-pair · gpt-3.5-turbo

    speculative phrases or statements that imply uncertainty or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    athing
    -0.76
    bread
    -0.71
    ohan
    -0.69
    raint
    -0.69
    rake
    -0.67
    Virgin
    -0.66
    ussions
    -0.65
    ride
    -0.65
    Driver
    -0.64
    verse
    -0.63
    POSITIVE LOGITS
     misunder
    0.87
     alternatively
    0.85
     incent
    0.76
     unintentional
    0.72
    idon
    0.70
     summarized
    0.70
    ©¶æ
    0.70
     argued
    0.69
     intu
    0.67
     exacerbated
    0.65
    Act Density 0.168%

    No Known Activations