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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "In" used to indicate the beginning of statements or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duct
    -0.23
    sofar
    -0.23
    odore
    -0.20
     spite
    -0.17
    wards
    -0.17
    ducted
    -0.17
    /by
    -0.17
     behalf
    -0.16
    depend
    -0.16
    adays
    -0.16
    POSITIVE LOGITS
     addition
    0.30
     additions
    0.24
     contrast
    0.23
     Addition
    0.23
     add
    0.23
     added
    0.22
     essence
    0.21
    contrast
    0.21
     sum
    0.20
     reality
    0.20
    Act Density 0.164%

    No Known Activations