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

    Neuronpedia

    INDEX
    Explanations

    terms related to empirical research and evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cag
    -0.92
    WaitGroup
    -0.86
    AccessFile
    -0.83
     StringTokenizer
    -0.83
     Roscoe
    -0.77
     dourada
    -0.77
     goats
    -0.77
    typeorm
    -0.77
    rinfo
    -0.76
    rovnik
    -0.74
    POSITIVE LOGITS
     Emb
    1.04
    Emb
    0.98
     Em
    0.95
     EMP
    0.94
     Emilie
    0.91
    Emilia
    0.90
     EMB
    0.88
     Emilia
    0.83
     EM
    0.83
    /');
    0.82
    Act Density 0.190%

    No Known Activations