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

    Neuronpedia

    INDEX
    Explanations

    names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ✭✭
    -0.49
     montré
    -0.46
    featureID
    -0.46
     riga
    -0.45
     compris
    -0.45
     montr
    -0.45
    thenReturn
    -0.45
     Pertama
    -0.45
    enlace
    -0.44
     autorytatywna
    -0.44
    POSITIVE LOGITS
     gallows
    0.67
     Rtl
    0.66
     destroyer
    0.66
     doubtnut
    0.64
     housekeeper
    0.63
     breeders
    0.62
    IContainer
    0.61
     heaters
    0.61
     horseman
    0.60
     blaster
    0.60
    Act Density 0.246%

    No Known Activations