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

    Neuronpedia

    INDEX
    Explanations

    instances of measurements or quantities described in an expressive or impactful way

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.77
     Majefty
    -0.68
     Nauka
    -0.62
    Composable
    -0.62
     Jefus
    -0.62
     kasarigan
    -0.61
     Monfieur
    -0.60
     Houſe
    -0.60
     RSSSF
    -0.60
    PerformLayout
    -0.60
    POSITIVE LOGITS
    CodeAttribute
    0.70
     AssemblyCompany
    0.60
     entire
    0.59
    (!__
    0.59
     literally
    0.56
    entire
    0.55
     protoimpl
    0.53
     halbe
    0.51
     scarcely
    0.51
     hardly
    0.50
    Act Density 0.330%

    No Known Activations