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

    Neuronpedia

    INDEX
    Explanations

    mentions of authorship or collaboration in academic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.85
    kloped
    -0.79
    LookAnd
    -0.78
     typelib
    -0.77
     Paglinawan
    -0.73
     ſche
    -0.71
    hoeddwyd
    -0.71
    Personensuche
    -0.71
     ſever
    -0.71
    OGND
    -0.70
    POSITIVE LOGITS
     estimés
    0.56
     stessa
    0.53
     stesso
    0.51
     himself
    0.51
    ,
    0.49
     selbst
    0.46
     stessi
    0.43
    достатки
    0.43
     benzina
    0.42
     rendah
    0.42
    Act Density 0.100%

    No Known Activations