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

    Neuronpedia

    INDEX
    Explanations

    character sequences and formatting elements typically found in code or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lan
    -0.41
    Lan
    -0.40
     ST
    -0.40
     LAN
    -0.39
     af
    -0.38
     sai
    -0.38
     wes
    -0.37
    Controllo
    -0.37
    Jg
    -0.37
     вот
    -0.37
    POSITIVE LOGITS
    IsContent
    0.60
     picioare
    0.55
     EconPapers
    0.53
    MergeFrom
    0.53
     فريبيس
    0.52
     distanciation
    0.51
    parsedMessage
    0.50
    arschijnlijk
    0.50
    aronder
    0.49
     zoude
    0.49
    Act Density 0.261%

    No Known Activations