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

    Neuronpedia

    INDEX
    Explanations

    negative expressions and themes related to social challenges and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.05
    3:0.05
    4:0.04
    5:0.03
    6:0.33
    7:0.20
    8:0.04
    9:0.06
    10:0.05
    11:0.04
    Negative Logits
    istries
    -1.32
    :{
    -1.32
    �
    -1.29
     Horizons
    -1.29
     destiny
    -1.25
     privileges
    -1.24
     royalties
    -1.24
     weights
    -1.20
     Membership
    -1.19
     props
    -1.19
    POSITIVE LOGITS
    imensional
    1.57
    gae
    1.54
     compr
    1.53
    ranged
    1.46
    aretz
    1.44
     sidx
    1.44
    umn
    1.44
    姫
    1.43
    immer
    1.42
    auc
    1.37
    Act Density 0.001%

    No Known Activations