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

    Neuronpedia

    INDEX
    Explanations

    references to timestamps and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.18
    3:0.07
    4:0.07
    5:0.03
    6:0.19
    7:0.07
    8:0.05
    9:0.05
    10:0.07
    11:0.13
    Negative Logits
    soType
    -1.51
     srfAttach
    -1.50
    acebook
    -1.40
    midt
    -1.39
    ェ
    -1.35
    minecraft
    -1.33
    Gam
    -1.31
    NYSE
    -1.31
    Unknown
    -1.22
    natureconservancy
    -1.22
    POSITIVE LOGITS
     Migration
    1.39
     introdu
    1.23
    lishes
    1.22
     Alfred
    1.22
     Krypt
    1.20
     Clive
    1.19
    DragonMagazine
    1.19
    ight
    1.18
    miah
    1.18
     Doct
    1.18
    Act Density 0.004%

    No Known Activations