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

    Neuronpedia

    INDEX
    Explanations

    mentions of instructions or guidance related to processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    webgl
    -0.85
     Neve
    -0.78
    AsUp
    -0.78
    endphp
    -0.77
     harem
    -0.77
    лерея
    -0.76
    ?>"
    -0.76
    ENTINA
    -0.76
     Kuz
    -0.76
     كومونز
    -0.75
    POSITIVE LOGITS
     instructions
    2.09
     instruction
    1.85
     Instructions
    1.78
    instructions
    1.67
     Instruction
    1.64
     INSTRUCTION
    1.58
    Instructions
    1.58
    Instruction
    1.55
    instruction
    1.52
     instruct
    1.49
    Act Density 0.049%

    No Known Activations