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

    Neuronpedia

    INDEX
    Explanations

    changes made within a system or process

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating changes or modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    horn
    -0.74
    quickShipAvailable
    -0.72
    MpServer
    -0.72
    wyn
    -0.63
     Cosponsors
    -0.62
    hent
    -0.62
    lehem
    -0.61
    Got
    -0.60
    CI
    -0.59
    owler
    -0.58
    POSITIVE LOGITS
     appease
    1.06
     accommodate
    0.98
     reflect
    0.94
     ensure
    0.94
     enhance
    0.89
     clarify
    0.87
     compensate
    0.86
     alleviate
    0.85
     improve
    0.84
     conserve
    0.83
    Act Density 0.092%

    No Known Activations