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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurements and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    олові
    -0.62
     surla
    -0.58
     Paglinawan
    -0.55
    iritto
    -0.55
    円
    -0.50
     nahilalakip
    -0.50
     Intelligen
    -0.50
     لينك
    -0.50
     pihaknya
    -0.49
     незавершена
    -0.49
    POSITIVE LOGITS
     xx
    0.58
     XX
    0.58
     arou
    0.55
     app
    0.54
     XXX
    0.54
     aproxim
    0.54
     above
    0.53
     One
    0.52
    classnames
    0.51
     around
    0.51
    Act Density 0.530%

    No Known Activations