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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations and administrative boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enfans
    -0.57
     Durban
    -0.44
     Miami
    -0.41
     Broward
    -0.40
     espin
    -0.40
    iNdEx
    -0.39
     grø
    -0.39
     Essex
    -0.39
     Essen
    -0.39
    amemnon
    -0.38
    POSITIVE LOGITS
     Canberra
    0.64
    TargetException
    0.61
    Anhalt
    0.59
    hassee
    0.56
    washingtonpost
    0.56
     otomatig
    0.55
    Capitol
    0.54
     Capitol
    0.54
    PropertyChanging
    0.54
    栃木
    0.54
    Act Density 1.407%

    No Known Activations