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

    Neuronpedia

    INDEX
    Explanations

    phrases related to arguments or claims being made or discussed

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

    said that or argue that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.59
     Majefty
    -0.52
     poffible
    -0.51
    oredCriteria
    -0.50
     houſe
    -0.49
     Kości
    -0.48
     undersø
    -0.47
    genodigd
    -0.47
     nových
    -0.47
    دانشنامهٔ
    -0.46
    POSITIVE LOGITS
    MathML
    0.40
    consulté
    0.38
    setTransform
    0.37
    TestTools
    0.37
    toThrow
    0.36
    AutoScale
    0.35
     onPause
    0.35
     keratin
    0.35
    glTex
    0.34
    FromArgb
    0.33
    Act Density 0.031%

    No Known Activations