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

    Neuronpedia

    INDEX
    Explanations

    terms related to "extra" or "additional" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    @[+][
    -0.80
    hObject
    -0.67
     AssemblyCompany
    -0.67
    ochond
    -0.66
    PreferredItem
    -0.65
     resourceCulture
    -0.65
    amssymb
    -0.65
    CopyWith
    -0.60
    WriteTagHelper
    -0.60
    stakes
    -0.60
    POSITIVE LOGITS
     Extra
    1.18
     EXTRA
    1.16
     extra
    1.13
    extra
    1.11
    Extra
    1.11
    EXTRA
    0.96
    ordinary
    0.93
     Extras
    0.90
    ordin
    0.89
     EXTR
    0.87
    Act Density 0.137%

    No Known Activations