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

    Neuronpedia

    INDEX
    Explanations

    the word "most" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emer
    -0.17
    iber
    -0.16
    IPP
    -0.15
    ги
    -0.14
    iper
    -0.14
    umd
    -0.14
     pair
    -0.14
     catch
    -0.14
    imals
    -0.13
    ental
    -0.13
    POSITIVE LOGITS
    /all
    0.18
     importantly
    0.17
    arda
    0.17
    elocity
    0.16
    eor
    0.16
    kü
    0.14
    actal
    0.14
    .scalablytyped
    0.14
    ELY
    0.14
    TRS
    0.14
    Act Density 0.034%

    No Known Activations