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

    Neuronpedia

    INDEX
    Explanations

    references to specific concepts or instructions in coding examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vak
    -0.66
     kol
    -0.65
     Cid
    -0.64
     geen
    -0.64
    mony
    -0.62
     Shub
    -0.62
     HttpHeaders
    -0.60
    PLY
    -0.60
    jours
    -0.60
     Rost
    -0.60
    POSITIVE LOGITS
     Lo
    1.80
    Lo
    1.72
     lo
    1.68
     LO
    1.56
    LO
    1.37
    lo
    1.29
     Loomis
    1.27
     Loth
    1.20
     Loeb
    1.16
     dello
    1.11
    Act Density 0.068%

    No Known Activations