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

    Neuronpedia

    INDEX
    Explanations

    specific structural components and features of buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     most
    -0.51
     determined
    -0.49
    ,
    -0.48
     indeed
    -0.45
    issus
    -0.45
    duos
    -0.44
    Билгалдахарш
    -0.44
    ParallelGroup
    -0.43
    älde
    -0.43
    grima
    -0.43
    POSITIVE LOGITS
     виправивши
    1.01
     tartalomajánló
    0.80
    RenderAtEndOf
    0.71
     onAnimation
    0.68
     betweenstory
    0.67
    Personensuche
    0.66
     '<?
    0.65
    
    0.65
    сылкі
    0.64
    bbene
    0.64
    Act Density 0.228%

    No Known Activations