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

    Neuronpedia

    INDEX
    Explanations

    numeric values associated with parameters in a technical or programming context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     useStyles
    -1.02
    NameInMap
    -0.94
     auroit
    -0.91
     dezelve
    -0.89
     feroit
    -0.88
     étoient
    -0.88
     comigo
    -0.87
     houſe
    -0.87
     plufieurs
    -0.85
     enfans
    -0.84
    POSITIVE LOGITS
    guri
    0.65
    eaus
    0.62
    Muz
    0.62
     sed
    0.61
    esk
    0.61
    ritsar
    0.61
     mer
    0.60
     Mercier
    0.58
     הר
    0.57
     Mur
    0.57
    Act Density 0.027%

    No Known Activations