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

    Neuronpedia

    INDEX
    Explanations

    references to comparison among different entities or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     []:
    -0.51
    c
    -0.45
    影
    -0.42
    わ
    -0.41
     _
    -0.40
     cup
    -0.40
    INTERNAL
    -0.40
    影子
    -0.39
     пря
    -0.39
    直
    -0.39
    POSITIVE LOGITS
     ProtoMessage
    0.88
    RenderAtEndOf
    0.84
     незавершена
    0.81
     EconPapers
    0.81
    rrggbb
    0.79
     AssemblyCompany
    0.74
    Vidite
    0.73
     linkovi
    0.73
    SharedDtor
    0.72
    Autoritní
    0.72
    Act Density 0.287%

    No Known Activations