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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zon
    -0.08
    _ASSUME
    -0.08
    客
    -0.08
    rani
    -0.08
    екÑģи
    -0.08
    efa
    -0.07
    ropa
    -0.07
    .volley
    -0.07
    éĢļãĤĬ
    -0.07
    Fuse
    -0.07
    POSITIVE LOGITS
     town
    0.07
     village
    0.07
     downtown
    0.06
     present
    0.06
     ras
    0.06
    _lazy
    0.06
     Hatch
    0.06
     city
    0.05
     Su
    0.05
     exit
    0.05
    Act Density 0.033%

    No Known Activations