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

    Neuronpedia

    INDEX
    Explanations

    references to locations, particularly cities and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.96
    protoimpl
    -0.78
    oredCriteria
    -0.75
    SourceChecksum
    -0.75
    ThroughAttribute
    -0.73
     ostavi
    -0.72
    FormState
    -0.72
    enderror
    -0.72
    matchCondition
    -0.66
    DebuggerStep
    -0.62
    POSITIVE LOGITS
     metropolitan
    0.71
     London
    0.65
     Paris
    0.63
     eixo
    0.62
     Chicago
    0.61
     Londra
    0.61
     Atlanta
    0.61
     City
    0.60
     city
    0.60
     suburbs
    0.59
    Act Density 0.133%

    No Known Activations