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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating purpose or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.14
    3:0.06
    4:0.16
    5:0.02
    6:0.05
    7:0.20
    8:0.05
    9:0.05
    10:0.09
    11:0.09
    Negative Logits
     fame
    -1.53
    bm
    -1.49
    wagon
    -1.45
     Mé
    -1.37
    river
    -1.37
    yards
    -1.35
     Jasper
    -1.35
    minist
    -1.34
    rams
    -1.32
    conservancy
    -1.31
    POSITIVE LOGITS
    ISA
    1.47
    Statement
    1.46
    OUGH
    1.45
    pecially
    1.38
    =~=~
    1.37
    sent
    1.36
    OFF
    1.35
     fit
    1.33
    -|
    1.33
    Prep
    1.33
    Act Density 0.000%

    No Known Activations