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

    Neuronpedia

    INDEX
    Explanations

    descriptions of giving or receiving something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a sense of providing or gaining insights and beneficial experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cipher
    -0.71
    asha
    -0.70
     Deaths
    -0.64
    ohm
    -0.62
    queue
    -0.61
    meet
    -0.61
    taboola
    -0.61
    gard
    -0.61
    lies
    -0.60
    ute
    -0.59
    POSITIVE LOGITS
     insight
    1.28
     glimpse
    1.18
     opportunity
    1.13
     chance
    1.12
     flexibility
    1.05
     advantage
    1.01
     impression
    0.99
     credibility
    0.94
     clue
    0.94
     indication
    0.92
    Act Density 0.232%

    No Known Activations