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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "defamatory."

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

    words starting with 'def'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beginnetje
    -0.50
    unternehmen
    -0.44
    awtextra
    -0.42
    thâu
    -0.42
     îles
    -0.41
    WriteLiteral
    -0.40
     Inscrivez
    -0.40
     Matériau
    -0.39
     Prancis
    -0.39
     jorden
    -0.39
    POSITIVE LOGITS
     def
    2.17
     deflate
    0.90
     deff
    0.87
     déf
    0.80
     DEF
    0.77
    def
    0.74
     deflect
    0.70
     deflation
    0.69
     Def
    0.68
     deflection
    0.66
    Act Density 0.009%

    No Known Activations