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

    Neuronpedia

    INDEX
    Explanations

    temperatures and temperature ranges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.11
    3:0.04
    4:0.06
    5:0.04
    6:0.05
    7:0.29
    8:0.06
    9:0.06
    10:0.12
    11:0.09
    Negative Logits
    geries
    -1.60
    cific
    -1.57
    staking
    -1.49
     collection
    -1.44
     amalg
    -1.44
    eday
    -1.44
    imentary
    -1.41
     presentations
    -1.40
     weddings
    -1.40
     reimb
    -1.38
    POSITIVE LOGITS
    flat
    1.48
     miserable
    1.46
    cius
    1.41
    instein
    1.37
     chilly
    1.34
    Ther
    1.33
     glare
    1.32
    atures
    1.32
     harsh
    1.28
     sunlight
    1.27
    Act Density 0.009%

    No Known Activations