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

    Neuronpedia

    INDEX
    Explanations

    phrases that express engagement or prompting interaction with the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.64
    Personendaten
    -0.56
    GraphicsUnit
    -0.56
     Theſe
    -0.56
    TestingModule
    -0.54
     therefore
    -0.53
    الإنجليزية
    -0.52
    Buildable
    -0.52
    classnames
    -0.52
     поэтому
    -0.50
    POSITIVE LOGITS
    utico
    0.58
     please
    0.58
    PerformLayout
    0.58
     nakalista
    0.58
    lamabad
    0.55
     réjou
    0.54
     touch
    0.53
    koff
    0.53
     try
    0.53
     make
    0.52
    Act Density 0.143%

    No Known Activations