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

    Neuronpedia

    INDEX
    Explanations

    references to instructions and their execution in a computing context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.66
     ModelExpression
    -0.65
     ComVisible
    -0.61
    ftest
    -0.59
    AsUp
    -0.58
    MigrationBuilder
    -0.58
     Becher
    -0.56
    最快更新
    -0.56
     समीक्षक
    -0.55
    karni
    -0.55
    POSITIVE LOGITS
    insn
    0.71
    նակ
    0.62
     cards
    0.57
    ForValue
    0.56
    isfile
    0.55
     bire
    0.55
     Cards
    0.52
    Opcode
    0.52
    dolce
    0.51
     aang
    0.51
    Act Density 0.010%

    No Known Activations