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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords, particularly function and class definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.65
     Италијани
    -0.62
    Tikang
    -0.60
     faſt
    -0.59
    addCriterion
    -0.58
     Photocase
    -0.57
     Comprometido
    -0.56
    oredCriteria
    -0.56
     ſtate
    -0.56
     myſelf
    -0.55
    POSITIVE LOGITS
    def
    1.98
     def
    1.56
     Def
    1.30
    Def
    1.27
    DEF
    1.04
     déf
    1.02
     DEF
    0.98
     deff
    0.82
     deflection
    0.82
    defs
    0.81
    Act Density 0.053%

    No Known Activations