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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advertisements or viewer engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.05
    2:0.07
    3:0.08
    4:0.05
    5:0.11
    6:0.08
    7:0.03
    8:0.09
    9:0.12
    10:0.10
    11:0.05
    Negative Logits
    rower
    -1.46
     mechanically
    -1.20
     finally
    -1.20
     neglig
    -1.20
     contracted
    -1.13
     contracting
    -1.12
     settled
    -1.12
     fortunate
    -1.11
     hereby
    -1.08
     gene
    -1.07
    POSITIVE LOGITS
    adders
    1.47
     rooft
    1.31
    interstitial
    1.28
    Iv
    1.27
     VIDEOS
    1.22
     裏�
    1.20
    cuts
    1.18
    smart
    1.17
    SPONSORED
    1.16
    �
    1.16
    Act Density 0.002%

    No Known Activations