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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to professionalism and appropriateness in social interactions and behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rar
    -0.45
     kampen
    -0.45
     pioggia
    -0.43
    orial
    -0.42
     complé
    -0.41
     atardecer
    -0.39
     alumínio
    -0.39
     sucesso
    -0.39
     estacionamento
    -0.38
     Estadística
    -0.38
    POSITIVE LOGITS
    EndContext
    1.02
     AssemblyCulture
    0.84
    SourceChecksum
    0.81
     resourceCulture
    0.79
    AccessFile
    0.79
    NSFW
    0.79
    nappropriate
    0.78
    PYX
    0.77
    addCriterion
    0.73
     kasarigan
    0.73
    Act Density 0.291%

    No Known Activations