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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and similar prepositions indicating actions or purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.14
    3:0.08
    4:0.18
    5:0.03
    6:0.04
    7:0.23
    8:0.03
    9:0.04
    10:0.05
    11:0.09
    Negative Logits
    ulia
    -1.81
    urally
    -1.68
    externalActionCode
    -1.65
     bedrooms
    -1.64
    Reviewer
    -1.58
     sizes
    -1.52
    assies
    -1.43
    mouth
    -1.40
    anooga
    -1.40
    gc
    -1.39
    POSITIVE LOGITS
     laure
    1.62
     millenn
    1.50
     dogged
    1.45
     POLIT
    1.37
     Perspect
    1.36
     techn
    1.32
    atha
    1.29
     srfAttach
    1.29
     pse
    1.28
     physicist
    1.27
    Act Density 0.001%

    No Known Activations