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

    Neuronpedia

    INDEX
    Explanations

    phrases related to addition or accumulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exact
    -0.30
     voer
    -0.29
    resizingMask
    -0.28
     collectively
    -0.28
     AssemblyTitle
    -0.27
     Abdullah
    -0.27
     handleSubmit
    -0.27
     roten
    -0.27
    includegraphics
    -0.27
     depend
    -0.26
    POSITIVE LOGITS
     addTo
    0.77
     Ergänzung
    0.75
    addTo
    0.72
     additions
    0.71
     menambah
    0.70
     addition
    0.70
    AddTo
    0.67
    0.65
     supplementing
    0.62
     Additions
    0.62
    Act Density 0.475%

    No Known Activations