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

    Neuronpedia

    INDEX
    Explanations

    notifications related to compliance and legal requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.05
    2:0.09
    3:0.05
    4:0.05
    5:0.06
    6:0.12
    7:0.03
    8:0.03
    9:0.30
    10:0.03
    11:0.03
    Negative Logits
    quad
    -3.87
     Jacobs
    -3.41
     GF
    -3.36
    Sac
    -3.35
     Brun
    -3.27
    265
    -3.24
    scar
    -3.19
     mitochond
    -3.18
     Spartan
    -3.09
    Soc
    -3.06
    POSITIVE LOGITS
     notices
    6.08
     notice
    6.06
    notice
    5.71
     Notice
    4.99
    Notice
    4.51
     NOTICE
    4.02
     notifications
    3.92
     notification
    3.89
     Notification
    3.74
     WARN
    3.48
    Act Density 0.003%

    No Known Activations