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

    Neuronpedia

    INDEX
    Explanations

    financial terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "initial"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rea
    -0.74
    pered
    -0.70
    alia
    -0.69
    Franc
    -0.68
    former
    -0.68
    âĹ¼
    -0.67
    ren
    -0.67
    Union
    -0.66
    _-
    -0.64
    yers
    -0.64
    POSITIVE LOGITS
     impressions
    1.08
    izers
    1.07
     stages
    1.06
    isers
    1.02
    izations
    0.98
    isation
    0.95
     indications
    0.94
    isations
    0.90
     impression
    0.88
    ization
    0.88
    Act Density 0.034%

    No Known Activations