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

    Neuronpedia

    INDEX
    Explanations

    expressions of suggestion, recommendation, or emphasis in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    introducing a statement with that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abetes
    -0.47
     Prepar
    -0.47
    stylers
    -0.46
    tribal
    -0.45
    ENEFITS
    -0.45
    Spoljašnje
    -0.45
    dchen
    -0.45
    ArrowToggle
    -0.45
    oleh
    -0.44
     Cog
    -0.44
    POSITIVE LOGITS
    IntoConstraints
    0.45
    MessageOf
    0.39
    PreExecute
    0.38
     autorytatywna
    0.38
     resourceCulture
    0.36
    enumi
    0.35
    AndEndTag
    0.34
    ">//
    0.34
     hochzeit
    0.34
     AssemblyCompany
    0.34
    Act Density 0.028%

    No Known Activations