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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performance metrics and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gameserver
    -0.60
    Datuak
    -0.56
     Jez
    -0.54
    Referències
    -0.54
     .
    -0.51
    loh
    -0.51
     Merrick
    -0.51
     SDR
    -0.51
    sivos
    -0.50
     
    -0.50
    POSITIVE LOGITS
     than
    1.06
     THAN
    0.91
     Than
    0.78
    Than
    0.75
    than
    0.71
    EndProject
    0.70
     any
    0.69
     saites
    0.69
     surpass
    0.68
    Kelebihan
    0.67
    Act Density 0.066%

    No Known Activations