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

    Neuronpedia

    INDEX
    Explanations

    terms related to citations or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.09
    2:0.09
    3:0.08
    4:0.08
    5:0.07
    6:0.06
    7:0.08
    8:0.08
    9:0.09
    10:0.08
    11:0.07
    Negative Logits
    EMA
    -3.09
    soType
    -2.92
    NRS
    -2.91
    ashtra
    -2.88
     Languages
    -2.80
    arnaev
    -2.77
    actionDate
    -2.76
     Mathematics
    -2.76
    mb
    -2.75
     Addiction
    -2.72
    POSITIVE LOGITS
     shuttle
    2.95
     Willow
    2.88
     hunts
    2.79
     Gret
    2.78
     Goose
    2.71
     ogre
    2.67
    riger
    2.65
    \/\/
    2.62
     Geral
    2.58
     flies
    2.56
    Act Density 0.000%

    No Known Activations