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

    Neuronpedia

    INDEX
    Explanations

    phrases with the pattern "to-X-to", where X can be a word or empty

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to vehicle-related topics or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     flares
    -0.69
     Hung
    -0.65
     modulation
    -0.64
     dependent
    -0.63
     affirmation
    -0.63
     messing
    -0.63
     sooner
    -0.63
     exploits
    -0.63
     Wiley
    -0.63
     indications
    -0.62
    POSITIVE LOGITS
    date
    1.19
    prison
    1.17
    advertising
    1.17
    itiveness
    1.15
    market
    1.13
    life
    1.12
    toe
    1.11
    gas
    1.10
    be
    1.10
    speech
    1.10
    Act Density 0.025%

    No Known Activations