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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "add" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .netbeans
    -0.15
    276
    -0.14
     Mild
    -0.14
    hur
    -0.14
    ampp
    -0.14
    à¥įपर
    -0.14
     supers
    -0.13
    .bam
    -0.13
    phony
    -0.13
    println
    -0.13
    POSITIVE LOGITS
    resse
    0.18
    endum
    0.16
    dera
    0.15
    icut
    0.15
    uctor
    0.15
    asin
    0.14
    ToBounds
    0.14
    ãĥ¥ãĥ¼
    0.14
    uce
    0.14
    ilos
    0.14
    Act Density 0.053%

    No Known Activations