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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating importance or significance in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Савезне
    -0.85
     Inscrivez
    -0.70
    脚注の使い方
    -0.65
    HasBeenSet
    -0.65
     nahilalakip
    -0.65
    Geplaatst
    -0.64
     laiss
    -0.64
    NameInMap
    -0.63
    antMatchers
    -0.63
     fraî
    -0.62
    POSITIVE LOGITS
    ❸
    0.58
    częściej
    0.51
    érale
    0.51
    PreInfinity
    0.51
    principalTable
    0.50
     support
    0.49
     समीक्षक
    0.49
     universal
    0.49
     easily
    0.49
     vital
    0.49
    Act Density 0.310%

    No Known Activations