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

    Neuronpedia

    INDEX
    Explanations

    prominent figures and events in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EClass
    -0.54
     iprot
    -0.53
    ########.
    -0.52
     automatiques
    -0.52
    ritation
    -0.52
     suivantes
    -0.49
    abras
    -0.49
     äta
    -0.48
     peccato
    -0.48
     ibland
    -0.46
    POSITIVE LOGITS
    verwijspagina
    0.70
    OGND
    0.66
    RegistryLite
    0.62
    baomidou
    0.62
    rungsseite
    0.61
     שוליים
    0.61
    DebuggerStep
    0.60
    FTFY
    0.60
    <bos>
    0.60
     kasarigan
    0.60
    Act Density 0.223%

    No Known Activations