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

    Neuronpedia

    INDEX
    Explanations

    phrases related to privacy and security terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.54
    hält
    -0.48
     Améli
    -0.43
     Vater
    -0.43
    を起こ
    -0.42
     piacere
    -0.41
    ecirc
    -0.41
     imb
    -0.39
    AC
    -0.39
    uarts
    -0.38
    POSITIVE LOGITS
    ivoli
    0.70
     Jefus
    0.64
     pinulongan
    0.63
    ंदीखरीदारी
    0.63
     LIRE
    0.63
    UnusedPrivate
    0.62
    principalColumn
    0.62
     Houſe
    0.62
     jogja
    0.61
    juvant
    0.61
    Act Density 0.033%

    No Known Activations