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

    Neuronpedia

    INDEX
    Explanations

    references to cities and geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.76
     ostavi
    -0.71
    ObjectContext
    -0.62
    DebuggerStep
    -0.58
    FormState
    -0.58
    TemporalType
    -0.55
    ällig
    -0.54
     aspect
    -0.54
    hasMoreElements
    -0.52
     pstmt
    -0.52
    POSITIVE LOGITS
     London
    0.91
     metropolitan
    0.84
     Tokyo
    0.83
    Tokyo
    0.79
    London
    0.78
     Londra
    0.76
     capitales
    0.76
     Seoul
    0.76
     Mumbai
    0.75
     Amsterdam
    0.75
    Act Density 0.182%

    No Known Activations