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

    Neuronpedia

    INDEX
    Explanations

    the word "Actually" or its variations, indicating a correction or emphasis in the discourse

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

    introduces clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.52
     kasarigan
    -0.50
    stdc
    -0.49
    thâu
    -0.49
     المعيارى
    -0.49
    InitVars
    -0.48
    JsonPropertyName
    -0.47
    :✨
    -0.47
    CodedInputStream
    -0.46
    цездатний
    -0.46
    POSITIVE LOGITS
    Actually
    0.74
     Actually
    0.68
     Nope
    0.47
    Nope
    0.44
    Maybe
    0.43
     Maybe
    0.43
    XmlAccessorType
    0.42
     Anyway
    0.40
     anyhow
    0.40
    Ой
    0.38
    Act Density 0.011%

    No Known Activations