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

    Neuronpedia

    INDEX
    Explanations

    negative sentences or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.08
    4:0.07
    5:0.09
    6:0.08
    7:0.08
    8:0.07
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
    ¨
    -3.62
    [/
    -3.26
    Avg
    -3.09
     Newport
    -2.96
    quickShipAvailable
    -2.96
     Connecticut
    -2.78
     Blizz
    -2.76
    ijn
    -2.75
     Melt
    -2.70
     Rhode
    -2.70
    POSITIVE LOGITS
    Org
    2.91
    merce
    2.75
     violently
    2.73
    Fight
    2.67
    Ur
    2.66
     violent
    2.44
    pose
    2.41
     submission
    2.41
    aunders
    2.41
    osate
    2.39
    Act Density 0.000%

    No Known Activations