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

    Neuronpedia

    INDEX
    Explanations

    verbs and their inflections related to sharpness or mental acuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.04
    3:0.06
    4:0.06
    5:0.03
    6:0.14
    7:0.35
    8:0.04
    9:0.04
    10:0.10
    11:0.04
    Negative Logits
    aea
    -1.78
    ylum
    -1.75
    aucuses
    -1.71
    Party
    -1.67
     confidentiality
    -1.66
     comr
    -1.63
    osponsors
    -1.61
    Privacy
    -1.60
     VIP
    -1.60
     willingly
    -1.59
    POSITIVE LOGITS
     strokes
    2.12
    sharp
    2.00
    stroke
    2.00
    gradient
    1.89
    stro
    1.82
    heet
    1.80
     nails
    1.80
     sharp
    1.77
     stroke
    1.75
     notch
    1.72
    Act Density 0.002%

    No Known Activations