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

    Neuronpedia

    INDEX
    Explanations

    references to different states and types of liquid substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.05
    3:0.04
    4:0.05
    5:0.03
    6:0.41
    7:0.11
    8:0.02
    9:0.04
    10:0.09
    11:0.07
    Negative Logits
    ilyn
    -1.43
    SPONSORED
    -1.40
     Achievements
    -1.31
    erella
    -1.31
    anza
    -1.30
    illac
    -1.28
    olphin
    -1.26
    venth
    -1.25
    MAC
    -1.25
    rentice
    -1.25
    POSITIVE LOGITS
     electroly
    1.49
    absor
    1.26
    inders
    1.25
    ク
    1.25
    Bytes
    1.23
     funnel
    1.22
     absorb
    1.21
    ocr
    1.21
    perse
    1.20
    ヘラ
    1.19
    Act Density 0.002%

    No Known Activations