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

    Neuronpedia

    INDEX
    Explanations

    repeated use of the word "or" in various contexts

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

    "Or" followed by a comparison word

    np_acts-logits-general · gemini-2.0-flash

    one or another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    újo
    -0.50
    BufferException
    -0.49
     hombros
    -0.45
    VersionUID
    -0.44
     Decke
    -0.42
     Kebijakan
    -0.42
    TypedDataSet
    -0.41
     Verhält
    -0.41
    ambung
    -0.41
    نیم
    -0.41
    POSITIVE LOGITS
    脚注の使い方
    0.47
    featureID
    0.46
    jsdelivr
    0.45
    XmlAccessorType
    0.45
    DebuggerStep
    0.43
    +#+#
    0.42
     Thal
    0.42
     ويكيميديا
    0.41
    RetentionPolicy
    0.41
    RequestMethod
    0.40
    Act Density 0.493%

    No Known Activations