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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating necessity or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.23
    3:0.12
    4:0.10
    5:0.03
    6:0.10
    7:0.13
    8:0.03
    9:0.04
    10:0.06
    11:0.07
    Negative Logits
     guiActive
    -2.00
     srfAttach
    -2.00
    版
    -1.61
    Dialogue
    -1.57
    actionDate
    -1.54
    tnc
    -1.54
    displayText
    -1.51
    VERTISEMENT
    -1.50
     [|
    -1.47
    り
    -1.46
    POSITIVE LOGITS
     incarcer
    1.80
     Bulgar
    1.72
    hetti
    1.66
     Vaugh
    1.55
     Barcl
    1.54
    gars
    1.52
     Ott
    1.52
     Thieves
    1.48
     Saudis
    1.47
    ngth
    1.41
    Act Density 0.001%

    No Known Activations