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

    Neuronpedia

    INDEX
    Explanations

    phrases pertaining to success and accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etting
    -0.17
    beros
    -0.17
    atsu
    -0.15
    å¼¹
    -0.14
    tract
    -0.14
    ignet
    -0.14
    initializer
    -0.14
    uby
    -0.14
    lok
    -0.14
     nackte
    -0.14
    POSITIVE LOGITS
    rad
    0.16
     cen
    0.14
    ctors
    0.14
    orsch
    0.14
    zen
    0.14
     Yen
    0.13
    595
    0.13
     Wass
    0.13
    zk
    0.13
    SCP
    0.13
    Act Density 0.078%

    No Known Activations