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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing time periods and their significance in experiences or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.19
    3:0.07
    4:0.10
    5:0.03
    6:0.11
    7:0.05
    8:0.05
    9:0.04
    10:0.21
    11:0.06
    Negative Logits
    vic
    -1.46
     Croat
    -1.46
    ゴン
    -1.43
    cephal
    -1.42
     throats
    -1.38
     Wrest
    -1.38
     Pul
    -1.38
    Enter
    -1.37
     parap
    -1.37
     Tycoon
    -1.36
    POSITIVE LOGITS
    oother
    1.76
    rontal
    1.58
    htaking
    1.51
    maxwell
    1.51
    continue
    1.50
    undreds
    1.49
    irmed
    1.49
    hovah
    1.49
     partName
    1.49
    regor
    1.47
    Act Density 0.004%

    No Known Activations