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

    Neuronpedia

    INDEX
    Explanations

    references to instructions and guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.68
     وتسجيلات
    -0.66
     linkovi
    -0.66
    存于互联网档案馆
    -0.66
    NameInMap
    -0.66
    politan
    -0.65
    AndEndTag
    -0.65
    بوابة
    -0.64
     חיצוניים
    -0.64
    bootstrapcdn
    -0.63
    POSITIVE LOGITS
     instructions
    2.33
     Instructions
    2.16
     instruction
    2.02
    instructions
    1.92
    Instructions
    1.86
     Instruction
    1.80
     INSTRUCTIONS
    1.77
     INSTRUCTION
    1.67
     instructed
    1.66
     instructs
    1.65
    Act Density 0.091%

    No Known Activations