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

    Neuronpedia

    INDEX
    Explanations

    words indicating a strong level of certainty or intensity

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing absoluteness or exclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukong
    -0.68
    umbnail
    -0.67
    ociate
    -0.67
    rongh
    -0.64
    DOM
    -0.63
    isode
    -0.63
     sacrific
    -0.63
    regate
    -0.60
    glers
    -0.60
    mage
    -0.59
    POSITIVE LOGITS
     conceivable
    1.11
     unclear
    1.01
     impossible
    0.99
     possible
    0.97
     ironic
    0.97
     doubtful
    0.94
     evident
    0.94
     advisable
    0.91
     obvious
    0.90
     raining
    0.89
    Act Density 0.217%

    No Known Activations