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

    Neuronpedia

    INDEX
    Explanations

    proper names or significant titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -1.03
    AndEndTag
    -0.97
     архивлан
    -0.91
     Monfieur
    -0.87
    存于互联网档案馆
    -0.87
    Tikang
    -0.86
    ConstraintMaker
    -0.86
    Sucesor
    -0.85
     Bioaccumulative
    -0.85
     виправивши
    -0.84
    POSITIVE LOGITS
    horst
    0.45
     déclaré
    0.44
     auprès
    0.42
     demás
    0.40
     américains
    0.39
     históricas
    0.38
     em
    0.38
     heureux
    0.37
     primeras
    0.37
     elett
    0.37
    Act Density 0.280%

    No Known Activations