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

    Neuronpedia

    INDEX
    Explanations

    mentions of terms related to legal agreements or contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oneofs
    -0.52
    packs
    -0.43
    Eureka
    -0.41
    WithIOException
    -0.40
    Geplaatst
    -0.40
     plaques
    -0.40
     clusters
    -0.40
    Còn
    -0.40
     Scranton
    -0.39
    Beaucoup
    -0.39
    POSITIVE LOGITS
     terms
    0.67
    Terms
    0.66
     Terms
    0.65
    terms
    0.60
     TERMS
    0.58
    GenerationType
    0.57
     modalités
    0.56
    TERMS
    0.52
     termes
    0.51
    条款
    0.50
    Act Density 0.031%

    No Known Activations