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

    Neuronpedia

    INDEX
    Explanations

    the mention of the year 2017

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates or time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iffe
    -0.71
    ril
    -0.71
     Guant
    -0.69
    rue
    -0.67
    avy
    -0.66
    rang
    -0.66
    èª
    -0.65
    olean
    -0.65
    reon
    -0.64
    ynes
    -0.64
    POSITIVE LOGITS
     pickups
    0.66
    luck
    0.64
     Poison
    0.63
     onions
    0.62
     Kinn
    0.62
    kas
    0.60
     poison
    0.59
    etsk
    0.58
     Resp
    0.57
     poisoning
    0.57
    Act Density 0.000%

    No Known Activations