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

    Neuronpedia

    INDEX
    Explanations

    the term "most" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llib
    -0.19
    odb
    -0.17
    peer
    -0.15
    oad
    -0.15
    tight
    -0.14
    .gdx
    -0.14
    atre
    -0.14
    ãģĵãģĿ
    -0.14
    iddi
    -0.13
    kbd
    -0.13
    POSITIVE LOGITS
    ellan
    0.16
    efa
    0.16
     importantly
    0.15
    ToMany
    0.15
     likely
    0.15
    owing
    0.15
    ethe
    0.15
    ecká
    0.15
    /latest
    0.14
    /all
    0.14
    Act Density 0.054%

    No Known Activations