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

    Neuronpedia

    INDEX
    Explanations

    patterns related to programming and code structure

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

    source code file paths and directory structures in code repositories.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     Rückkehr
    -0.49
     Töchter
    -0.47
     Menschheit
    -0.47
     Tatsache
    -0.47
     laiko
    -0.45
     raggiunto
    -0.45
     célèbres
    -0.45
    eseorang
    -0.45
     Verpackung
    -0.44
     historiador
    -0.44
    POSITIVE LOGITS
     GenerationType
    0.56
    󠁬
    0.55
    tagHelperRunner
    0.52
    yntaxException
    0.52
    IntoConstraints
    0.51
    "])
    0.50
     ProtoMessage
    0.50
    MERC
    0.48
    erval
    0.47
    Ɓ
    0.47
    Act Density 0.667%

    No Known Activations