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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mauritania
    -0.92
    writeFieldEnd
    -0.88
    +#+#
    -0.76
    äumt
    -0.76
     Dorchester
    -0.75
    Personensuche
    -0.74
    ReusableCell
    -0.74
     troy
    -0.74
    adaptiveStyles
    -0.73
     ब्रेकडाउन
    -0.72
    POSITIVE LOGITS
    hibernate
    0.58
     Croatia
    0.57
     Cinque
    0.56
     чере
    0.56
     Drone
    0.56
     drone
    0.55
    Croatia
    0.54
     Marin
    0.54
    tahankan
    0.53
    rvats
    0.53
    Act Density 0.674%

    No Known Activations