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

    Neuronpedia

    INDEX
    Explanations

    comments and code structure in programming language syntax

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

    English natural language text mixed with code comments and explanations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    OGND
    -0.41
    viewDid
    -0.38
     мәкал
    -0.37
     voors
    -0.36
    conio
    -0.35
     iParam
    -0.34
    Personendaten
    -0.34
    évaluateur
    -0.33
     يتيمه
    -0.33
    VersionUID
    -0.32
    POSITIVE LOGITS
     calculate
    0.65
     prepare
    0.65
     assign
    0.61
     update
    0.60
     preparing
    0.59
     determine
    0.59
     prepares
    0.59
     store
    0.57
     retrieve
    0.57
     check
    0.56
    Act Density 0.747%

    No Known Activations