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

    Neuronpedia

    INDEX
    Explanations

    the presence of references to guidelines or official regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ë§ŀ
    -0.15
    ype
    -0.15
    abin
    -0.15
    iegel
    -0.15
    cente
    -0.15
    glas
    -0.14
    hk
    -0.14
    fak
    -0.14
    ä½į
    -0.14
    inati
    -0.14
    POSITIVE LOGITS
    andy
    0.16
     namespace
    0.15
     cap
    0.15
    ardy
    0.14
    aked
    0.14
     gang
    0.14
    aque
    0.14
     neutral
    0.14
     Sale
    0.13
     ard
    0.13
    Act Density 0.147%

    No Known Activations