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

    Neuronpedia

    INDEX
    Explanations

    references to registers in computing or programming contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    intoxic
    -0.62
     Sanderson
    -0.61
     mencer
    -0.60
    Nationalité
    -0.60
    kommen
    -0.60
    Azur
    -0.59
    ‬
    -0.58
    er
    -0.58
    ☼
    -0.58
     lâng
    -0.57
    POSITIVE LOGITS
     REG
    0.98
    PerformLayout
    0.91
    REG
    0.90
    ंदीखरीदारी
    0.90
     Reg
    0.88
    Reg
    0.87
     reg
    0.83
     CommonModule
    0.83
    CppMethod
    0.81
    WriteAttribute
    0.81
    Act Density 0.008%

    No Known Activations