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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appId
    -0.14
    otel
    -0.14
    htdocs
    -0.14
    iese
    -0.14
    anging
    -0.14
     Hanging
    -0.14
    ì¶ĺ
    -0.14
    мена
    -0.13
    è¡Ĺéģĵ
    -0.13
    vim
    -0.13
    POSITIVE LOGITS
     home
    0.28
     located
    0.28
     situated
    0.26
    located
    0.23
     reached
    0.23
    sit
    0.23
     within
    0.21
    Sit
    0.20
     part
    0.20
     across
    0.20
    Act Density 0.087%

    No Known Activations