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

    Neuronpedia

    INDEX
    Explanations

    references and definitions related to terminology in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elman
    -0.16
    PLICIT
    -0.15
    лÑĥÑĩ
    -0.15
    pliant
    -0.14
    erli
    -0.14
    iver
    -0.14
    .runtime
    -0.14
    .son
    -0.13
    Fight
    -0.13
    efe
    -0.13
    POSITIVE LOGITS
     terms
    0.50
    terms
    0.42
     terminology
    0.41
     Terms
    0.41
    Terms
    0.38
     termin
    0.37
     TERMS
    0.35
     gloss
    0.35
     Gloss
    0.35
    _terms
    0.34
    Act Density 0.109%

    No Known Activations