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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names with common occurrences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "briefly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IRO
    -0.75
    DIT
    -0.73
    Absolutely
    -0.72
    Reviewer
    -0.70
    atorial
    -0.70
    Eva
    -0.69
    ador
    -0.65
    holes
    -0.65
    massive
    -0.65
    Quality
    -0.65
    POSITIVE LOGITS
     glimps
    1.08
     briefly
    0.86
     interrupted
    0.85
     separated
    0.84
     glimpse
    0.77
     glance
    0.76
     stint
    0.75
     interrupt
    0.74
     paused
    0.74
    mares
    0.72
    Act Density 0.011%

    No Known Activations