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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their distributions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.94
    uxxxx
    -0.92
     الحره
    -0.91
    MLLoader
    -0.89
     autorytatywna
    -0.83
    WireFormatLite
    -0.81
     <<<<<<<<<<<<<<
    -0.79
    Jeografia
    -0.79
     surla
    -0.78
    tanleria
    -0.78
    POSITIVE LOGITS
     
    0.48
     téléphonique
    0.46
     trône
    0.44
    aság
    0.44
    éges
    0.44
    PRESSED
    0.42
    itative
    0.42
     angusti
    0.41
    HttpPut
    0.41
     مبارک
    0.40
    Act Density 0.369%

    No Known Activations