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

    Neuronpedia

    INDEX
    Explanations

    phrases or statements expressing doubt, skepticism, or disagreement

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of trust in information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oliath
    -0.61
    uto
    -0.59
    lot
    -0.57
     awarding
    -0.56
    por
    -0.56
    xon
    -0.55
    opian
    -0.55
    holm
    -0.55
     whence
    -0.54
    ivating
    -0.54
    POSITIVE LOGITS
     happens
    1.46
     happened
    1.36
    soever
    1.33
     transpired
    1.21
     constitutes
    1.17
     occurs
    1.07
     appears
    1.06
     else
    1.00
     exists
    0.99
     belongs
    0.97
    Act Density 0.099%

    No Known Activations