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

    Neuronpedia

    INDEX
    Explanations

    strong affirmations or declarations of certainty

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

    definitely followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.63
    ScopeManager
    -0.55
    runApp
    -0.54
     כך
    -0.50
    charest
    -0.49
    UserScript
    -0.49
    CppCodeGen
    -0.49
    帖最后由
    -0.48
     termica
    -0.48
    scriptId
    -0.47
    POSITIVE LOGITS
     definitely
    1.98
    definitely
    1.77
    Definitely
    1.66
     Definitely
    1.65
     definately
    1.37
     definite
    1.25
     certainly
    1.23
    definite
    1.16
    certainly
    1.16
     definitivamente
    1.16
    Act Density 0.004%

    No Known Activations