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

    Neuronpedia

    INDEX
    Explanations

    keywords related to computer programming, specifically compilers

    oai_token-act-pair · gpt-3.5-turbo

    instances of the root "comp" related to composition or compounded items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iken
    -0.81
    hyde
    -0.80
    osta
    -0.76
    arten
    -0.74
    adan
    -0.73
    TN
    -0.71
     Sturgeon
    -0.71
    Ul
    -0.67
    aan
    -0.66
    anyahu
    -0.66
    POSITIVE LOGITS
     comp
    3.76
     Comp
    1.74
    comp
    1.64
    Comp
    1.52
     compilation
    1.34
     compartment
    1.29
     recomp
    1.28
     decomp
    1.23
     COMP
    1.14
     compens
    1.09
    Act Density 0.016%

    No Known Activations