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

    Neuronpedia

    INDEX
    Explanations

    references to the use of substances in various contexts, particularly in studies or research settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.12
    3:0.05
    4:0.08
    5:0.02
    6:0.07
    7:0.32
    8:0.03
    9:0.03
    10:0.10
    11:0.10
    Negative Logits
    etheless
    -1.99
    minded
    -1.57
    eeper
    -1.57
    hearted
    -1.56
    emetery
    -1.56
    nown
    -1.54
    neck
    -1.46
     attitude
    -1.46
    heartedly
    -1.44
    abre
    -1.41
    POSITIVE LOGITS
    版
    1.54
     AFP
    1.46
     viz
    1.45
     Manufact
    1.35
     interchangeable
    1.28
     Spice
    1.28
     QC
    1.28
    ories
    1.27
     interchange
    1.26
     Chong
    1.26
    Act Density 0.025%

    No Known Activations