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

    Neuronpedia

    INDEX
    Explanations

    phrases encouraging interaction with online platforms and subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.09
    3:0.15
    4:0.12
    5:0.03
    6:0.04
    7:0.12
    8:0.11
    9:0.06
    10:0.06
    11:0.10
    Negative Logits
     describ
    -1.43
     perce
    -1.41
    eway
    -1.33
     quer
    -1.24
     tram
    -1.23
    unin
    -1.23
     gorilla
    -1.20
     ability
    -1.20
     tending
    -1.19
    icans
    -1.19
    POSITIVE LOGITS
    hetti
    1.45
    Alternatively
    1.42
    mods
    1.38
     �
    1.31
    etsy
    1.31
    odcast
    1.30
    Mini
    1.28
     attRot
    1.27
    Enjoy
    1.27
    Original
    1.27
    Act Density 0.023%

    No Known Activations