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

    Neuronpedia

    INDEX
    Explanations

    prepositions that indicate spatial or contextual relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    equila
    -0.44
    meliharaan
    -0.42
     Superhost
    -0.42
    */].
    -0.42
    ateľ
    -0.40
     sementes
    -0.39
    المصادر
    -0.39
     mempertahankan
    -0.39
     giornal
    -0.39
     penyel
    -0.38
    POSITIVE LOGITS
     cross
    0.97
     across
    0.97
     ACROSS
    0.91
     Across
    0.90
    across
    0.89
    cross
    0.87
     Cross
    0.84
     CROSS
    0.84
    Across
    0.84
     crossing
    0.81
    Act Density 0.101%

    No Known Activations