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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a sense of direction or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.70
    ndham
    -0.70
    ]")]
    -0.67
     Rumania
    -0.63
    TEntity
    -0.61
     Bebe
    -0.60
     ITU
    -0.59
     Wicidata
    -0.58
     Diſ
    -0.58
     ZEALAND
    -0.58
    POSITIVE LOGITS
     ALONG
    1.14
     Along
    1.06
     along
    1.05
    Along
    1.03
    along
    0.97
    mybatisplus
    0.95
     lungo
    0.77
    ArgsConstructor
    0.69
    pentine
    0.69
     langs
    0.68
    Act Density 0.120%

    No Known Activations