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

    Neuronpedia

    INDEX
    Explanations

    terms related to research and scientific inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.24
    3:0.10
    4:0.08
    5:0.03
    6:0.06
    7:0.07
    8:0.06
    9:0.04
    10:0.12
    11:0.11
    Negative Logits
    zac
    -1.75
     Tags
    -1.73
     Likes
    -1.67
    estones
    -1.61
     Runes
    -1.55
     guiName
    -1.53
    Quantity
    -1.51
     =>
    -1.47
     Medals
    -1.47
     Saur
    -1.45
    POSITIVE LOGITS
    alore
    1.87
    uctor
    1.87
    outhern
    1.77
     convened
    1.75
    ridor
    1.71
    ioch
    1.68
    ORGE
    1.67
     chaired
    1.62
    amera
    1.62
     inspector
    1.61
    Act Density 0.000%

    No Known Activations