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

    Neuronpedia

    INDEX
    Explanations

    the concept of remembering and its various forms in language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    finder
    -0.16
    adal
    -0.15
    vig
    -0.15
    fighter
    -0.14
    rego
    -0.14
    yb
    -0.14
     Cra
    -0.14
    otch
    -0.14
    uring
    -0.14
     Merrill
    -0.14
    POSITIVE LOGITS
    hoff
    0.15
     bid
    0.15
    ald
    0.15
    isd
    0.14
     saja
    0.14
     childhood
    0.14
    ously
    0.14
    οÏįν
    0.14
    ous
    0.13
    ãĥ³ãĥIJ
    0.13
    Act Density 0.031%

    No Known Activations