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

    Neuronpedia

    INDEX
    Explanations

    references to locations and distances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.11
    3:0.04
    4:0.08
    5:0.02
    6:0.05
    7:0.33
    8:0.03
    9:0.02
    10:0.09
    11:0.15
    Negative Logits
    ��
    -1.48
    ETS
    -1.47
    uates
    -1.35
     anticipation
    -1.34
    iked
    -1.34
    wine
    -1.31
    spir
    -1.30
    ヘ
    -1.30
     Fever
    -1.30
    peat
    -1.30
    POSITIVE LOGITS
     Scalia
    1.39
     Spawn
    1.36
     Plaint
    1.26
     Brother
    1.23
     Defendant
    1.23
    amental
    1.22
     Pie
    1.21
     avenues
    1.15
     Rutherford
    1.15
     Plaintiff
    1.13
    Act Density 0.006%

    No Known Activations