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

    Neuronpedia

    INDEX
    Explanations

    terms related to IP addresses and access control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orden
    -0.18
    orte
    -0.16
    enville
    -0.16
    ylon
    -0.14
    andalone
    -0.14
    ãĥ¼ãĥľ
    -0.13
    eldon
    -0.13
     Yan
    -0.13
    agli
    -0.13
    itesse
    -0.13
    POSITIVE LOGITS
     alien
    0.15
    äºĭ
    0.15
    anium
    0.15
     fds
    0.14
     Vet
    0.14
    osu
    0.14
     Lindsey
    0.14
     visiting
    0.14
    629
    0.14
    igo
    0.14
    Act Density 0.543%

    No Known Activations