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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments and language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.07
    3:0.06
    4:0.06
    5:0.05
    6:0.23
    7:0.12
    8:0.07
    9:0.03
    10:0.09
    11:0.12
    Negative Logits
    Products
    -1.51
     Painter
    -1.43
    Admin
    -1.41
    zos
    -1.37
     XD
    -1.37
    ":["
    -1.36
    cients
    -1.30
    ONSORED
    -1.29
     Bought
    -1.28
     Thumbnails
    -1.24
    POSITIVE LOGITS
    accompan
    1.72
    ensity
    1.49
    ileged
    1.45
    Enlarge
    1.44
    church
    1.40
    ngth
    1.36
    dden
    1.35
     rebellion
    1.31
     caffe
    1.29
     boredom
    1.28
    Act Density 0.014%

    No Known Activations